satellite-mcp

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v0.1.0
Disambiguation4/5
Tools are organized by clear category prefixes (e.g., agri_, aircraft_, conflict_) with distinct operations. A few clusters like firms_active_area/country/point and aircraft_live/search have overlapping purposes but descriptions differentiate by query method. Overall, most tools are easily distinguishable.
Naming Consistency5/5
All tool names follow a consistent category_verb_noun pattern in snake_case (e.g., geo_distance, change_burn). No mixing of camelCase or other conventions. Even special tools like satellite_list_sources fit the pattern. Exceptional consistency across 171 tools.
Tool Count2/5
171 tools is excessive for a single MCP server. Many tools could be merged with parameters (e.g., spectral indices, change detection indexes, FIRMS queries). This volume overwhelms agent tool selection and increases cognitive load, reducing practical coherence.
Completeness4/5
The server covers an extremely broad range of domains (agriculture, conflict, cyber, environment, trade, weather, etc.) with thorough sub-tool sets. Missing a few niche capabilities (e.g., flood mapping from satellite imagery, refined demographic data) but overall feels complete for its intended scope.
Average 3.5/5 across 171 of 171 tools scored. Lowest: 2.8/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 4 commits in the last 12 weeks
- Last stable release on June 30, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is failing
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description fails to disclose behavioral traits such as read-only nature, data freshness, or output format. The agent is left without knowing what happens when invoking the tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Very concise at one sentence, but it is a noun phrase lacking structure or front-loading of key information. The brevity sacrifices clarity on tool behavior.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema or annotations, the description is the sole source of information. It does not specify what the output looks like (e.g., text alerts, coordinates), leaving the agent poorly equipped to use the tool. Incomplete for a tool that could benefit from more context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has zero parameters, so the description is not required to document parameters. However, it does not explicitly state that no parameters are needed, missing an opportunity to clarify usage. Baseline for no-param tool is 4, but the omission reduces it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly identifies the tool as providing desert locust swarm tracking and alerts from FAO Locust Watch. It distinguishes from sibling tools (e.g., agri_crop_health) by specifying a unique resource and source, though it lacks a strong action verb.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., other agri_ tools). No exclusions or prerequisites are mentioned, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as permissions, rate limits, or side effects. The tool's output format or type is not mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, very concise, but lacks necessary details. It is not front-loaded with critical information beyond the basic purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description is incomplete. It does not explain what the tool returns (e.g., list of base names, coordinates, or other attributes), leaving the agent without sufficient context for invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but parameter descriptions are minimal ('East longitude'). The tool description adds that these parameters define a bounding box, which is helpful but does not go beyond the schema's inherent semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Find' and resource 'naval bases and military ports', differentiating it from sibling tools like mil_bases (all bases) and mil_nuclear. It implicitly indicates a spatial query.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool over siblings. The bounding box context is implied but not contrasted with other tools that might also perform spatial searches, such as mil_bases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It states it fetches metadata and requires an API key, but does not clarify if it is read-only, the nature of the metadata, rate limits, or response structure. This is insufficient for safe agent invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, but it is under-specified for a tool with two parameters and no output schema. While efficient, it sacrifices necessary detail, earning a middling score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no output schema, no annotations, and two parameters, the description should explain what metadata is returned and how to use it. It fails to provide this, leaving significant gaps for an agent to understand the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds no extra meaning beyond the schema's parameter descriptions ('Planet item ID', 'Item type'). It does not provide examples or clarify usage context, so it meets but does not exceed the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves detailed metadata for a Planet Labs item, which is a specific verb-resource pair. This distinguishes it from sibling tools like planet_search (searching for items) and planet_stats (statistics), though it doesn't elaborate on what 'metadata' entails.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions the requirement of PLANET_API_KEY but provides no guidance on when to use this tool versus alternatives like planet_search or planet_thumbnail. It lacks context on prerequisites (e.g., obtaining an item_id) or usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full burden. It discloses the filtering mechanism (ICAO24 hex ranges) but omits behavioral traits like read-only nature, data volume, or required permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It efficiently conveys the tool's core action and method.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with sibling tools covering similar aircraft and military domains, the description lacks explanation of ICAO24 hex ranges, output format, and specific use cases. It is insufficient for an agent to fully understand the tool's scope.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides full descriptions for all four bounding box parameters. The description does not add information beyond the schema; thus it meets the baseline but does not exceed it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool filters military aircraft in a bounding box using ICAO24 hex ranges. It distinguishes itself from generic aircraft tools and military activity tools, though it does not explicitly compare to sibling tools like 'mil_aircraft'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'mil_aircraft' or 'aircraft_live'. The usage context is implied but not explicitly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden of behavioral disclosure. It only states that the tool provides status information, but does not clarify if it is read-only, what data source or freshness is used, or any rate limits. The agent cannot infer safety or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise, consisting of one short sentence that is front-loaded with the key purpose. It wastes no words. However, it may be too concise, lacking sufficient detail for an agent to fully understand the tool's behavior.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description should provide some indication of the output structure (e.g., returns a list of crises with requested and received amounts). It does not. The tool is simple with one parameter, but the lack of output context reduces completeness. Sibling tools exist but are not differentiated.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has a single optional parameter 'year' with a schema description stating it defaults to the current year. The tool description does not add any additional meaning beyond what the schema already provides. Since schema coverage is 100%, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly indicates the tool reports on humanitarian funding status with a comparison of requested vs received amounts for crises. This distinguishes it from sibling tools like humanitarian_crises (which list crises) and humanitarian_displacement (which tracks displacement). However, it could be more specific about the scope (e.g., per crisis, global aggregate).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. Sibling tools such as humanitarian_crises or humanitarian_reports could offer related information, but the description does not help the agent decide which is appropriate. There is no mention of prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, but it only states the basic purpose. It does not mention auth needs, rate limits, side effects, or output format. The read-only nature is implied but not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the core purpose. It is concise with no wasted words, though it could add a bit more context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema and no annotations, so the description should explain what the user can expect as output (e.g., a numeric radiance value, units). It does not, leaving the agent uninformed about the return type. Given the rich set of siblings, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters described minimally as 'Latitude' and 'Longitude'. The tool description adds only 'for a location', which does not provide additional semantic meaning beyond the schema. A score of 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'night light radiance estimate', and specifies a location. It distinguishes from siblings like nightlights_tile or nightlights_timeseries by focusing on a single-point estimate, but could be more explicit about the output type.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus the many sibling nightlights tools (e.g., anomaly, compare, timeseries). No context about when not to use it or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It does not mention data source, update frequency, units, resolution, or any limitations. The description only gives a high-level purpose without behavioral traits, which is insufficient for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence that conveys the core purpose without any fluff. It is appropriately sized and front-loaded, earning its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 required params, no output schema), the description lacks essential details such as what the output looks like (e.g., number, unit, time reference). Without annotations, this gap is significant for an agent to correctly interpret results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both 'lat' and 'lng' described as latitude and longitude. The description adds no additional meaning to the parameters beyond what the schema already provides, so it meets the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides ocean chlorophyll concentration as a reference for fishing productivity and marine ecosystems. It uses a specific resource (chlorophyll concentration) and distinguishes itself from sibling ocean tools by focusing on chlorophyll. However, it could be more explicit about the action (e.g., 'returns' or 'retrieves').
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives like env_water_quality or ocean_buoy_data. The description lacks any context about when it is appropriate or not, and no exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description is very brief and does not disclose any behavioral traits (e.g., read-only, authentication needs, rate limits, or data freshness). Since no annotations are provided, the description carries the full burden, which it fails to meet.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise, with one sentence covering the core purpose. It wastes no words, but could be slightly more front-loaded with a verb. Overall, efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema and a simple input, so the description should explain what the output includes (e.g., time series, area, maps). It only says 'reference', which is vague. An agent cannot determine what kind of data to expect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with one parameter 'region' described as 'Polar region'. The tool description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides 'Sea ice extent information' for Arctic and Antarctic, which is a specific data resource. It distinguishes from sibling tools like ocean_buoy_data or ocean_sst_anomaly. However, it lacks a verb like 'retrieve' or 'get', which slightly reduces precision.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other ocean or sea-ice related tools (e.g., env_ocean_temp). No when-not or alternative suggestions are provided, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behaviors. It only states the tool is an indicator for El Nino/La Nina. It does not mention that it returns a value, requires permissions, or any side effects. This is insufficient for a data retrieval tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that efficiently conveys the tool's subject and use. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no output schema and no annotations, the description is too sparse. It does not explain what the anomaly value represents, its range, time period, or how to interpret results. More context is needed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already provides meaning for lat and lng. The description adds no additional parameter context (e.g., units, data range). Baseline 3 is appropriate as it does not harm but also does not enhance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool is for sea surface temperature anomaly and connects it to El Nino/La Nina and climate monitoring. However, it lacks an explicit verb like 'retrieves' or 'gets', which would clarify the action. It differentiates from sibling tools like ocean_chlorophyll by focusing on anomaly, but not explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description implies use for climate monitoring but does not give explicit when-to-use or when-not-to-use context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does not disclose whether the tool is read-only, any destructive behavior, or rate limits. For a query tool, read-only behavior is implied but not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no fluff. However, it could be slightly expanded to include output type or example without losing conciseness. Still effective and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and simple input, description is minimally adequate. It covers what the tool finds but lacks details on return format or any caveats. Could mention that results are OSM features.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage with parameter descriptions (south, west, north, east). Description groups output types but adds no extra meaning to parameters. Baseline 3 is appropriate as schema already documents parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool finds industrial sites, power plants, and refineries within a bounding box. It is specific about the types of features, but could better distinguish from siblings like osm_infrastructure which may cover similar categories.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as osm_infrastructure or osm_buildings. The description implies usage for industrial features but provides no when-not-to-use or contextual cues.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states the basic purpose without revealing traits such as data recency, return format, pagination, authentication requirements, or rate limits. This is insufficient for an agent to anticipate the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no extraneous information. It is front-loaded with the action and resource. However, it could benefit from a slight structure (e.g., listing data source or return type) without adding verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 parameter, no output schema, no annotations), the description is minimally adequate. It identifies the data source (UNHCR) but lacks information on what the output looks like (e.g., data format, fields). For a tool with no output schema, the description should hint at return structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of parameter descriptions, so the baseline is 3. The description adds no additional meaning beyond the schema's 'Country name or 3-letter ISO code', making it neutral—neither helpful nor harmful.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get'), the resource ('displaced population data'), and the source ('from UNHCR'). It distinguishes the tool's focus on UNHCR data, but does not explicitly differentiate it from the sibling tool 'humanitarian_displacement', which likely covers similar displacement data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'humanitarian_displacement'. It does not specify prerequisites, context, or exclusion criteria, leaving the agent to infer usage from the tool name and description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states the source of data (UN WPP) but does not disclose traits like data freshness, units of growth, or any potential limitations. The description is minimal and fails to inform the agent about side effects, rate limits, or operational characteristics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with zero waste. Every word adds value: 'Population growth data for a country from UN World Population Prospects.' Perfectly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is low-complexity (1 param), but there is no output schema. The description does not explain what the output contains (e.g., yearly growth, percentage, historical range). Without the output schema, the description should compensate by describing the return format or structure, which it does not. Incomplete for an agent relying on the description alone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond what the input schema already provides for the 'country' parameter (country name or 3-letter ISO code). No additional semantics or usage notes are given.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides 'Population growth data for a country' from a specific source (UN World Population Prospects). The verb 'data' and resource 'country' are clear, but it does not explicitly differentiate from sibling tools like pop_age_structure or pop_density, though the 'growth' qualifier implies distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives. There are no when-to-use/when-not-to-use instructions, nor any mention of context or prerequisites. The description assumes the user knows when to request population growth data.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosure. It only states the tool's function without addressing any behavioral traits such as input constraints, output format, or operational limits (e.g., coordinate system, revisit frequency). This is minimal disclosure for a tool that likely queries external data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that communicates the core purpose without waste. It is front-loaded but lacks any structural elements like bullet points or separated sections, which are not critical for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and annotations, the description should provide more context about return values, usage constraints, or example use cases. The minimal description leaves the agent guessing about what information is returned and how to interpret it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% as both lat and lng have descriptions in the schema. The description adds only 'for a location', which is already implicit from lat/lng. No additional semantic value beyond the schema is provided, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides Sentinel-2 coverage and revisit information for a location, specifying both the resource (Sentinel-2) and the type of data. It is distinct from sibling tools like sentinel_latest or sentinel_search, though it does not elaborate on the exact scope of 'coverage and revisit information'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as sentinel_search or sentinel_latest. The agent must infer its purpose from the name and minimal description, which is insufficient for effective selection among many sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description alone must cover behavioral traits. It only states it returns a URL, but does not disclose whether the URL is temporary, requires authentication, or has any rate limits or data freshness constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that efficiently conveys the tool's purpose. It is front-loaded and avoids extraneous words, though it could briefly mention the output format.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema), the description is minimal but lacks details about the return value format, possible constraints, or how to use the output. It is incomplete for a well-rounded tool definition.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents the parameter as 'Copernicus product ID.' The tool description adds no additional semantic value beyond the schema, meeting the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get quicklook (thumbnail preview) URL for a Sentinel-2 product,' using a specific verb and resource. It distinguishes itself from sibling tools like sentinel_metadata, sentinel_download_url, and sentinel_search by focusing on the thumbnail preview.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, such as needing a product ID from sentinel_search, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry full behavioral transparency. It only says it lists satellites, with no details on side effects, rate limits, output, or safety. This is minimal for an external API call.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences and very concise. However, it could include more detail without being verbose, so it loses one point for missing potentially helpful structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters, no output schema, and no annotations, the description is too brief. It lacks information about output format, limitations, or how the API key is used, making it incomplete for an agent to use effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All four parameters have descriptions in the input schema (100% coverage), so the description adds no extra semantics. Baseline is 3, and there is no additional parameter information in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'List satellites currently overhead at a location', using a specific verb and resource. However, among siblings like space_passes, space_satellites, space_starlink, it does not differentiate its unique function of current overhead satellites.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions the need for an N2YO API key, but provides no guidance on when to use this tool over siblings, nor any context about prerequisites beyond the key, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must carry the full burden. It states 'List active satellites' implying a read-only operation, but does not disclose return format, pagination, authentication requirements, or any limitations. The behavior is underspecified for safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that efficiently conveys the tool's purpose. It is well-structured for quick parsing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple parameter set and lack of output schema, the description provides adequate but not complete context. It does not explain return values or edge cases, and given the many sibling tools, more completeness would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers 100% of parameters with an enum and description. The description repeats the enum values in prose, adding marginal clarity. No additional semantic information beyond the schema is provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and resource 'active satellites', and specifies filtering by category with enumerated examples. However, it does not distinguish this tool from siblings like space_starlink or space_tle, which may overlap in functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as space_starlink, space_debris, or satellite_list_sources. The agent has no information about trade-offs or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description lacks behavioral details: what does 'top' mean? What is the output format? Any limitations or pagination? Not disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words. Could be slightly expanded to include key details, but it is concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and high sibling variety, the description is insufficient. It does not explain what the output looks like (e.g., list of countries, rankings, values) or how 'top' is determined.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions for all parameters (country, year, flow). Description does not add additional meaning beyond schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Get', resource 'top trade partners', and scope 'for a country'. However, it does not differentiate from sibling tools like trade_flow or trade_timeseries, which might also return trade partner data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., trade_flow, trade_balance). No prerequisites or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It mentions an API key requirement, which is useful, but does not explain what the output looks like, whether it is a read-only operation, or any rate limits or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and front-loaded with purpose, but it sacrifices completeness. It is appropriately sized for a simple tool but could include more detail without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and 5 parameters, the description is incomplete. It does not explain the return value format, possible limitations, or edge cases. For a pass prediction tool, this is insufficient for a complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers 100% of parameters with descriptions, so the baseline is 3. The tool description adds no additional parameter information beyond stating the API key requirement, which is not a parameter itself.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it predicts visible satellite passes, which is a specific verb and resource. It distinguishes from sibling tools like 'space_overhead' by specifying 'visible', making the scope clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description only notes the requirement for a N2YO API key, but provides no guidance on when to use this tool versus alternatives like space_overhead or space_satellites. No when-not-to-use or usage context is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden of behavioral disclosure. It only lists weather indicators used but fails to describe computational cost, data sources, response format, or any side effects. This is insufficient for an assessment tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence that conveys the core purpose without extraneous words. It is concise, though it could incorporate additional useful information without sacrificing brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, and the description does not explain what the tool returns (e.g., drought index, categorical risk). Given the tool's analytical nature, the description should clarify output format, data timeliness, or interpretation. It falls short.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with well-defined lat/lng. The description adds context about weather indicators used but does not elaborate on parameter ranges, units, or how they affect results. Baseline 3 is appropriate as schema already documents the parameters adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Drought assessment at a location using weather indicators', specifying the verb (assess), resource (drought), and key inputs. It distinguishes itself from sibling tools like agri_crop_health by focusing narrowly on drought.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as agri_famine_risk or agri_crop_health. The description does not mention prerequisites, limitations, or excluded use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the data source (ACLED) but does not disclose any behavioral traits such as rate limits, return format, pagination, or update frequency, which is insufficient for a tool of this complexity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. However, it could be slightly more informative without becoming verbose, hence not a perfect 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 5 parameters and no output schema, the description is minimal. It does not explain the return format, default behavior (e.g., date range), or how to interpret results, leaving the agent underinformed for effective usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description lists event types which maps to the event_type parameter, but the schema already documents that. No additional meaning is added beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'armed conflict events from ACLED', listing specific event types (battles, violence against civilians, etc.), which distinguishes it from siblings like conflict_actors, conflict_fatalities, and conflict_hotspots.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus alternatives, nor does it mention exclusions or prerequisites. It simply states what the tool does without contextualizing usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behaviors. It lacks details on what exactly is returned (e.g., list of points, properties), whether there are any limits, or how the search is performed beyond using OSM data. This is insufficient for an agent to anticipate tool behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the core purpose. It is efficiently written, although it could include more critical details without becoming overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and the simplicity of the tool, the description should clarify what the agent can expect as output (e.g., list of landing points with properties). It does not, leaving the agent uncertain about the result format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for its three parameters (lat, lng, radius_km). The description does not add additional meaning beyond the schema definitions, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it finds submarine cable landing points near a coordinate using OpenStreetMap data. It uses specific verbs and resource, distinguishing it from sibling tools like 'infra_cables' which focus on cables themselves, not landing points.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or comparison with sibling tools that might also deal with submarine cables or infrastructure.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavioral traits. It only says 'reference data,' implying a read operation, but does not explicitly state read-only, data freshness, or whether multiple indicators are returned. No details on permissions or side effects are provided.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 12 words, efficiently conveying the core purpose without unnecessary detail. It is front-loaded and every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description hints at return fields ('chlorophyll, turbidity') but lacks units, temporal scope, or response structure. For a simple two-parameter tool, it is adequate but could be more informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with basic descriptions ('Latitude', 'Longitude'). The tool description adds 'for a coordinate' but does not enhance parameter meaning (e.g., coordinate system or precision). Baseline 3 is appropriate as the description repeats the schema's intent without adding value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as providing water quality indicators (chlorophyll, turbidity) for a coordinate. It uses a specific verb ('reference data') and resource ('water quality indicators'), and it distinguishes from siblings like env_air_pollution or env_ocean_temp by focusing on water quality parameters.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. The description does not state when to use this tool versus alternatives, nor does it mention any preconditions or exclusions. Among siblings, there is a potentially overlapping tool like ocean_chlorophyll, but no differentiation is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only says it finds pipelines with a geographic bounding box, but does not disclose what is returned, any limitations, or side effects. This is insufficient for a read tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. However, it is so concise that it omits useful context, balancing efficiency with some lack of detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and annotations, the description should provide more context about what is returned and how it differs from similar tools. It currently lacks completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the parameters are well-described with bounds. The description adds no extra meaning beyond the schema, which is acceptable given the coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Find' and clearly identifies the resource as 'oil, gas, and water pipelines in a bounding box,' which distinguishes it from sibling tools like infra_power or infra_cables.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention exclusions or comparison to similar inputs like infra_energy or infra_power.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It does not state whether the tool is read-only, if it requires authentication, or any constraints like rate limits. The description only hints at the phenomena detected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that conveys the key purpose without unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is somewhat incomplete. It does not explain the return format or how anomalies are defined, but it is sufficient for a simple tool with well-named parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter having a description. The description does not add additional meaning beyond the schema, so a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the purpose: detecting anomalies in night lights indicating power outages, conflict, or development. However, it does not differentiate from sibling tools like nightlights_compare or nightlights_timeseries, which may also deal with changes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description implies its use for anomaly detection but does not specify contexts or provide usage examples.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only restates the function without mentioning limitations, return format, or any side effects. The bounding box constraint is already in the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that conveys the core purpose efficiently with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a simple spatial query without an output schema, the description is adequate but could be more informative about the returned data structure or typical use cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters are already described. The description adds no extra meaning beyond the schema, earning the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool finds airports, airfields, and helipads within a bounding box, which is a specific verb-resource combination. It is distinct enough from siblings like osm_buildings or osm_query, although it does not explicitly name alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., osm_query for more general OSM queries). There are no when-not or context hints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only mentions the API key requirement. With no annotations, additional behavioral details (e.g., rate limits, data freshness, error handling) are missing. The agent is left uninformed about important traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with 10 words. Highly efficient and front-loaded. However, it could benefit from a brief note on output format or parameter usage without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 5 parameters and no output schema, the description is too sparse. It does not explain what 'coverage statistics' entails (e.g., temporal resolution, data types), nor how to interpret the interval parameter. Sibling diversity increases need for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond 'for an area' and does not clarify how parameters like interval affect the result. Schema already provides sufficient descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('Planet imagery coverage statistics') for a specific area. It distinguishes itself from sibling tools like planet_search (search scenes) and planet_metadata (get metadata) by specifying 'coverage statistics'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The only contextual hint is the requirement for PLANET_API_KEY, but no when-not-to-use or comparisons to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states that it gets an estimate but does not disclose output format, error behavior, or any side effects. A 2 reflects minimal transparency beyond the basic operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that is front-loaded with the core purpose. No wasted words; it efficiently conveys the tool's function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is insufficient. It does not explain the return value format (e.g., people per km^2), data source limitations, or how to handle edge cases like invalid coordinates. Agents may struggle to interpret the output correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter described. The description adds value by clarifying that the tool accepts either a coordinate (lat/lng) or a country code, which is not explicitly stated in the schema. This helps agents understand proper usage patterns.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get population density estimate' with specific scope (coordinate or country) and data source (WorldPop). It distinguishes the tool from sibling population tools like pop_growth by targeting density specifically, though it could be more explicit about what differentiates it from other pop_* tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool over alternatives, such as pop_age_structure or pop_growth. There is no mention of prerequisites, constraints, or scenarios where this tool is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the search criteria, omitting important details such as result ordering, pagination limits, default values, error handling, or whether the query is exhaustive. This is minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence that front-loads the core action. No extra words, but given the tool's complexity (9 parameters, many siblings), it could benefit from slightly more detail without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 9 parameters, 2 required, and no output schema. The description does not explain what the output contains, default behavior (e.g., limit=50, min_magnitude=1), how the bounding box is used, or the relationship between parameters. This leaves gaps for an agent to understand invocation requirements.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so each parameter already has a description in the input schema. The tool description does not add further semantic context (e.g., typical values, constraints, or usage tips) beyond the schema. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Search') and clearly identifies the resource ('earthquakes') and filtering criteria ('by date range, magnitude, and geographic region'). It effectively distinguishes the tool from siblings like 'quake_area' or 'quake_detail' by specifying the search scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus alternatives (e.g., 'quake_recent', 'quake_stats'). It lacks explicit conditions or exclusions, forcing the agent to infer usage from sibling names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are given, and the description does not disclose behavioral traits such as idempotency, authentication requirements, rate limits, or potential side effects. The agent is left to assume it is a safe read operation, but this is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence with no unnecessary words. It could be improved by adding structure (e.g., bullet points) but remains effective and concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is too brief for a tool with no output schema. It does not indicate what metadata fields are returned, the response format, or any constraints. For a metadata retrieval tool, more detail is needed to allow the agent to judge if it meets the need.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (product_id is documented as a UUID). The description does not add any new parameter information beyond what the schema provides, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'detailed metadata for a Sentinel-2 product', and the identifier 'by ID'. This distinguishes it from sibling tools like sentinel_bands, sentinel_download_url, and sentinel_latest, which have different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. For example, it does not explain when to prefer this over sentinel_bands or sentinel_search, nor does it mention prerequisites or whether it is for single or batch queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description fails to disclose behavioral traits such as data source latency, definition of a gap, or any limitations. The agent cannot infer reliability or scope from the description alone.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that conveys the core purpose without waste. It could be slightly expanded without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema and the description does not indicate what the response contains (e.g., list of gap events, timestamps). The agent lacks information about the tool's output format or additional behavioral context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameters are already documented. The description adds no extra meaning beyond what the schema provides, meeting the baseline for this dimension.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the verb 'Detect' and the resource 'AIS gap events (dark periods) for a vessel', with additional context about potential sanctions evasion or illegal activity. This effectively distinguishes it from sibling tools like ship_track or ship_position.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus alternatives (e.g., ship_track or ship_search). No when-not-to conditions or explicit context for usage are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It does not disclose behavioral traits such as whether the data is real-time or historical, pagination, date range capabilities, rate limits, or any other usage constraints. The description adds no behavioral insight beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one sentence) and front-loaded with the key purpose. However, it lacks any structural elements like bullet points. For a single-parameter tool, this conciseness is acceptable but could be slightly more informative without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of an output schema and the simple input, the description should explain what the tool returns (e.g., list of port visits with timestamps and port names). It fails to provide this essential context, leaving the agent uncertain about the output format and completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already fully describes the single parameter (vessel_id as 'GFW vessel ID') with 100% coverage. The description does not add additional meaning, such as how to obtain the vessel ID or the expected format. Baseline score 3 as schema covers the parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get port visit history for a vessel.' clearly states the action (Get) and resource (port visit history for a vessel). It distinguishes well from sibling tools like ship_position or ship_track, which focus on current position or movement tracks rather than historical port visits.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as ship_track or ship_position. There is no mention of prerequisites (e.g., needing a GFW vessel ID), nor any indication of typical use cases or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It does not disclose behavioral traits like whether the tool is read-only, what data is accessed, or any potential side effects. The description only mentions a reference classification without further detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise single sentence with no redundant information. Front-loaded with the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and simple input, the description fails to explain what the assessment returns (e.g., classification levels, regions, dates). It leaves the agent uncertain about the tool's output and scope.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (one parameter), and the description adds minimal value: it mentions FEWS NET IPC but does not explain expected country format or any constraints beyond the schema's 'Country name'. Baseline 3 is appropriate as schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is a famine risk assessment using FEWS NET IPC phase classification, specifying the verb (assess) and resource (famine risk), and distinguishes from sibling tools like agri_crop_health or agri_drought.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives such as other agricultural or humanitarian tools. The description is a single statement without any context on appropriate use cases or when to avoid.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states that it returns flight path waypoints, but does not disclose rate limits, authentication needs, data range, or whether it is read-only. Critical behavioral traits like output limits or required permissions are omitted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It immediately states the action, input, and output. While very brief, it is not under-specified for purpose; every element earns its place in the sentence.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description does not specify the structure of waypoints (e.g., lat/lon/timestamp), time range, or whether it supports historical or real-time data. No output schema exists to compensate. Given the tool's tracking nature and sibling context, more detail is needed for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (the single parameter 'icao24' has a description). The tool's description merely repeats the parameter's purpose ('by ICAO24 hex address') without adding new meaning or usage details. Baseline 3 is appropriate since the schema already covers the parameter adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Track a specific aircraft'), the resource ('by ICAO24 hex address'), and the output ('returns flight path waypoints'). It distinguishes effectively from siblings like aircraft_live or aircraft_waypoints by specifying 'track' and 'waypoints'. This is a specific verb+resource combination with no ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as aircraft_waypoints or aircraft_live. There are no prerequisites, limitations, or context for selecting this tool over siblings. The description only states what it does, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description explains the computation (NDVI difference) but does not disclose behavioral traits like side effects (none expected), permissions, rate limits, or whether it is read-only. With no annotations, this is insufficient disclosure for a tool that performs a computation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (two sentences) and front-loads the main purpose. However, it could be slightly more structured by explicitly stating the output or interpretation. No excess words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 4 required parameters and no output schema, the description adequately covers the inputs and method but lacks details on output format (e.g., NDVI values, difference classification). It is minimally complete for a computation tool but has clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with parameter descriptions already covering the inputs (NIR and red reflectance). The description adds context about NDVI but does not provide additional details beyond what the schema offers. Baseline score 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly identifies the tool's purpose: vegetation change detection using NDVI from two dates. It specifies the method (NDVI) and the inputs (NIR and Red band reflectance values), making it distinct from generic change detection tools like 'change_detect' or spectral tools like 'spectral_ndvi'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs. alternatives such as 'change_detect', 'change_urban', 'change_water', or 'spectral_ndvi'. The description does not mention prerequisites, limitations, or scenarios where this tool is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It states it provides an 'overview' but does not reveal whether it is read-only, how data is aggregated, or any limitations. The term 'assessment' is ambiguous.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that leads with the core purpose. It is efficient but could include more context without harming conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description covers the basic purpose. However, it lacks details on the output format, the meaning of 'assessment,' and how it compares to sibling tools, leaving gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter (country_code). The description adds no additional semantic value beyond the schema's own description of '2-letter ISO country code.' Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies a clear verb-resource pair: 'Country internet connectivity overview' with enumerated components (IXP count, cable landings, assessment). This differentiates it from specific sibling tools like cyber_ix_points and cyber_cable_landing, which focus on individual data types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus its siblings. The description does not mention prerequisites, exclusions, or alternative tools for more granular data.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It does not disclose behavior such as whether results are real-time or historical, what specific data is returned (e.g., outage severity, time range), or any side effects. The description is too vague to inform an agent about the tool's internal workings.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise and front-loaded. However, it could be slightly more informative without sacrificing brevity, hence 4 rather than 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (one parameter, no output schema), the description is minimally adequate. It lacks details on return format or expected behavior, but for a straightforward detection tool, it meets basic needs.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides full coverage for the single parameter 'country' with a clear description ('2-letter ISO country code'). The description adds no additional semantic value beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: detect internet outages in a country using IODA. It has a specific verb (Detect), resource (internet outages), and scope (in a country), which distinguishes it from sibling tools like cyber_connectivity or cyber_censorship.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., cyber_connectivity for general connectivity data). The description does not mention prerequisites, exclusions, or context for when an agent should prefer this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the basic behavior (search news via GDELT) but does not reveal limitations like data freshness, scope, or whether results are real-time or historical. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the tool's purpose. Every word is meaningful, and there is no redundancy or extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks information about the return format (e.g., what fields are returned) and does not explain what GDELT is. For a search tool with siblings, more context is needed to understand output and when it differs from similar tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameter descriptions in the schema are sufficient. The tool description adds no extra meaning beyond what the schema already provides for query, mode, and limit. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches news articles via GDELT for specific topics, locations, or events. The verb 'search' and resource 'news articles' are specific, but it does not differentiate from sibling tools like events_media or conflict_events, which may overlap.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The description lacks context about prerequisites, when not to use, or when other tools (e.g., events_media) would be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but fails to disclose behavioral traits such as output format, data source details beyond GDELT, rate limits, or authorization needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no waste, but could benefit from additional structure (e.g., separate usage note).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple parameter set and no output schema, the description provides the core purpose but lacks specification of output type or behavior, leaving the agent partially uninformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds slight context by mentioning 'topic or region' which relates to the query parameter, but does not elaborate on date formats or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'track' and resource 'news volume over time for a topic or region via GDELT', distinguishing it from sibling tools like 'events_global' which track actual events.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide guidance on when to use this tool versus alternatives, nor does it specify prerequisites or conditions for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only states it retrieves reports but does not disclose behavior like authentication needs, rate limits, or response structure. Fails to compensate for missing annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise and front-loaded with the key action. Could briefly mention usage context but overall efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and simple tool, description provides minimal context. It doesn't specify the format or content of results, leaving the agent guessing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with parameter descriptions, so baseline is 3. Tool description adds no extra meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'Get', resource 'humanitarian situation reports', and source 'ReliefWeb', distinguishing it from siblings like humanitarian_camps or humanitarian_crises.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as humanitarian_crises or humanitarian_displacement. The description provides no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description lacks any behavioral details such as return format, pagination, authentication, or rate limits. Minimal information beyond basic function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single concise sentence, front-loaded with key information. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema; description does not mention return values, data structure, or limitations. Incomplete for an agent to understand the full behavior without additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage with brief descriptions (e.g., 'East longitude'). The description adds 'bounding box' context but no additional semantics beyond schema. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'Find' and specific resources 'cell towers, communication masts, and data centers' constrained by a bounding box. Distinguishes from sibling tools like infra_cables and infra_energy.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Only describes function without context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must fully disclose behavior. It states the tool computes a composite score but does not explain how the score is calculated, its range, or what 'overall assessment' entails. Critical behavioral details are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence (17 words) that immediately conveys the tool's core function and components. No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, but the description does not hint at the output format (e.g., numeric score, confidence level). The combination of components is vague, leaving the agent uncertain about what will be returned.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with basic lat/lng descriptions. The description adds no further semantic detail beyond the bounding box usage. Since the schema already documents parameters well, the baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies a composite military activity score for a bounding box, combining facility count, restricted airspace, and overall assessment. This clearly distinguishes it from sibling tools that focus on individual military aspects like aircraft or bases.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like mil_bases or mil_airspace. The description does not mention when-not to use it or provide context for selection among the many military-related siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as data sensitivity, update frequency, required permissions, or any limitations. For a tool that may involve sensitive military data, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that immediately states the tool's purpose. It is concise and front-loaded, with no unnecessary words or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, and the description does not explain what the output contains (e.g., list of sites with names, coordinates, status). Given the lack of output schema and annotations, the description should provide more context about the results and any constraints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with all four bounding box parameters described with min/max and a short label. The tool description adds no additional parameter-level context beyond what the schema already provides, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Find') and clearly identifies the resource ('known missile test sites, launch pads, and military testing ranges'). It distinguishes from siblings like mil_bases (general bases) and mil_activity (general activity) by focusing on missile-specific infrastructure.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus sibling tools such as mil_bases, mil_activity, or mil_nuclear. There is no mention of prerequisites, alternatives, or scenarios where this tool is appropriate or not.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It does not disclose behavioral traits such as data source, update frequency, rate limits, or output format. Only states the basic function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that is clear and to the point. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no annotations. Description lacks context on what the tool returns (e.g., list of stations, coordinates, metadata). For a tool with 4 parameters and no structured output info, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions for south, west, north, east. Description adds no additional meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description states 'Find radar stations and air defense installations in a bounding box.' This is a specific verb and resource, clearly distinguishing it from sibling tools like mil_bases (bases) or mil_aircraft (aircraft).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like mil_activity or mil_airspace. No mention of prerequisites, limitations, or use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must convey behavioral traits. It only states that the tool returns a tile URL but omits details like data freshness, tile format, authentication needs, or rate limits, leaving the agent uninformed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with 10 words, concisely stating the tool's purpose. It is front-loaded and efficient, though it could include more context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity, the description is minimally complete but lacks details about the return value (e.g., that it's a string URL). Without an output schema, the agent may need to infer the response format, which is a gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, providing clear meanings for all four parameters. The description adds no further information, so the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the verb 'Get', the resource 'night lights map tile URL', and the source 'NASA GIBS — VIIRS Black Marble layer'. It clearly distinguishes this tool from sibling tools like nightlights_anomaly or nightlights_compare, which provide different types of data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. Without explicit context or exclusion criteria, an agent cannot determine if this is the best tool for a given request.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states the action is to 'Get' information, implying a read operation, but lacks details on data freshness, rate limits, or any side effects. More context is needed for safe agent use.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 7 words, front-loading the purpose with no extraneous information. Every word contributes to understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description omits critical context such as the structure of the returned data, any limitations, or environmental assumptions. For a tool with only two parameters, more completeness would improve usability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description does not add any meaning beyond what the parameter descriptions already provide (lat, lng with min/max and ocean location context).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves 'ocean current information' for a 'marine location', using a specific data source (Open-Meteo). The verb 'Get' and resource 'ocean current information' are specific and distinct from sibling ocean tools like ocean_buoy_data or ocean_chlorophyll.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, no exclusion criteria, and no information about prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description should fully disclose behavior. Only mentions API key requirement, but doesn't explain error handling, rate limits, or what happens if item_id is invalid.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise two sentences with no unnecessary words. Information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Does not explain return format, error handling, or relationship to other planet tools. For a simple tool, more detail would be helpful given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema covers both parameters with descriptions, so description adds no additional meaning. Baseline 3 as schema coverage is 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Get' and resource 'thumbnail preview URL for a Planet Labs item'. It distinguishes from siblings like planet_metadata, planet_search, etc. by specifying the action and resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Only mentions prerequisite 'Requires PLANET_API_KEY', but provides no guidance on when to use this tool versus alternatives like planet_search or planet_metadata.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry behavioral info. It states 'cloud-free' but doesn't explain how cloud cover is determined (default max_cloud=20 from schema) or what happens if no suitable image exists. Output format is not mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words. It front-loads the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 3-parameter tool with no output schema, the description is too minimal. It omits what the tool returns (e.g., image URL, thumbnail, metadata) and error behavior, leaving the agent to infer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so parameters are already documented. The description adds no extra meaning beyond the schema, matching the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Find the most recent cloud-free Sentinel-2 image for a location' clearly states the verb (Find), resource (Sentinel-2 image), and key qualifiers (most recent, cloud-free, for a location). It distinguishes from siblings like sentinel_search (historical search) and sentinel_timeline (time series).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no guidance on when to use this tool versus alternatives like sentinel_search for historical queries. It lacks explicit context for when-not-to-use or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It mentions 'detect encounters and transfers' but lacks details on data sources, update frequency, limitations, or what constitutes an encounter.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no waste, front-loaded with the essential purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool detecting complex events like ship encounters, the description lacks explanation of output, required parameters range, or data behavior, making it incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions for vessel_id, start_date, end_date. Description adds no new meaning beyond schema, achieving baseline score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies 'Detect ship-to-ship encounters and transfers for a vessel' with clear verb and resource, and adds context 'potential at-sea transshipment', distinguishing it from sibling tools like ship_position or ship_track.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like ship_search or ship_dark. The description implies it is for detecting encounters for a specific vessel but does not provide exclusions or context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only mentions included data fields (departure/arrival airports) but omits details on data limits, sorting, error handling, authentication, or whether the operation is read-only. The description is insufficiently transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words, front-loading the main action and key details. It is appropriately concise but could be slightly more informative without sacrificing brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description does not adequately explain return values or data format. It mentions 'including departure and arrival airports' but omits pagination, limits, and error conditions, leaving significant gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (all three parameters have descriptions). The tool description adds no additional meaning beyond the schema, aligning with the baseline score. No extra param semantics are provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets flight history for an aircraft over a time period, including departure and arrival airports. It uses a specific verb 'get' and resource 'flight history', distinguishing it from sibling tools like aircraft_live or aircraft_track.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like aircraft_live or aircraft_arrivals. Context is implied but not stated, leaving agents to infer usage from the purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden but only states the basic function. It fails to disclose behavioral traits such as data source, update frequency, pagination behavior, whether it is a read-only operation, or any rate limits. The description is too minimal for a tool with no annotation support.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, front-loading the core purpose. However, it is overly minimal and lacks structure. It could be improved by adding a brief note on output or usage context without adding significant length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and the tool's function of returning actors with event counts, the description does not explain the response format, data source, or any sorting/pagination behavior. With over 200 sibling tools, the contextual completeness is insufficient for an agent to fully understand how to interpret the results or integrate this tool with others.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already describes both parameters. The tool description does not add any additional meaning beyond the schema; it merely restates the function. The schema's description for 'limit' says 'Maximum events to analyze' which may be misleading for a tool that returns actors, but the description does not clarify this. Baseline 3 is appropriate as the description adds no extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List', the resource 'armed groups and actors', and the scope 'active in a country with event counts'. It distinguishes this tool from siblings like conflict_events (lists events) and conflict_fatalities (lists fatalities) by focusing on actors/groups.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for listing armed groups with event counts, but provides no explicit guidance on when to use this tool versus alternatives like conflict_events or conflict_hotspots. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral context. It only mentions data source and purpose but fails to disclose whether the tool returns data immediately, requires authentication, has rate limits, or what side effects exist. This is insufficient for a tool with no structural safety hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no redundant words. It front-loads the core purpose and ends with the data source, making it easy to parse. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 2-parameter tool with no output schema, the description omits what the output looks like or how results are structured. Given the minimal complexity, a basic description of return type or format would enhance completeness. Currently, it's adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with lat and lng described as 'Latitude' and 'Longitude'. The description adds no additional meaning beyond the schema. Baseline 3 is appropriate since the schema already handles parameter documentation adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks for methane emission hotspots using Sentinel-5P TROPOMI data. The verb 'Check' and resource 'methane emission hotspots' are specific, and it distinguishes itself from sibling tools like env_air_pollution by focusing on methane and citing a specific satellite data source.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., env_air_pollution for general air quality). There is no mention of prerequisites, limitations, or context for usage, leaving the agent to infer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It does not explain what 'active' means, data freshness, pagination, or any behavioral traits. Basic transparency is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with essential information, front-loaded with verb+resource. No superfluous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with one parameter, the description is adequate but lacks details about return format or source reliability. Slightly below complete given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with one parameter (limit) documented in schema. The description adds no additional meaning or context beyond the schema, meeting baseline but not exceeding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it lists active humanitarian crises from ReliefWeb, specifying the source and scope. It distinguishes from sibling tools like humanitarian_reports (reports) and humanitarian_camps (camps) by focusing on 'crises'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance provided on when to use this tool versus alternatives like humanitarian_reports or conflict_events. No prerequisites, exclusions, or context for using it in a workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral transparency. It does not disclose if the tool is read-only, any rate limits, data freshness, or response format. For a retrieval tool, critical behavioral traits are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no superfluous words. Every part is relevant and earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given a single optional parameter and no output schema, the description is minimally complete. It provides the source and categories but omits what the output looks like, data format, or time range. It is adequate but could be more informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (year has a description 'Year for statistics'), so baseline 3 applies. The tool description adds no further semantics about the parameter, such as valid range or behavior when omitted. It barely adds value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Global displacement statistics — refugees, IDPs, asylum seekers from UNHCR,' specifying the resource (displacement statistics), source (UNHCR), and categories (refugees, IDPs, asylum seekers). It distinguishes from sibling tools like humanitarian_camps and pop_displacement by naming the specific data and source.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives, such as pop_displacement or humanitarian_camps. The description implies use for UNHCR displacement stats but does not provide conditions, exclusions, or comparisons to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotation (none provided), the description only mentions USGS authentication. It does not disclose rate limits, URL expiration, error handling, or read-only nature. For a tool fetching a URL, more behavioral context is needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the core purpose, followed by the authentication requirement. No unnecessary words, clear structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter tool with no output schema, the description is adequate but lacks details on URL format, temporary vs permanent, and error conditions. It meets minimum viability but has gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with a description for entity_id. The tool description adds no extra semantics beyond what the schema already states, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get download URL' and the resource 'Landsat scene', distinguishing it from sibling tools like landsat_metadata or landsat_search. It is specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, such as landsat_search or sentinel_download_url. The only context is the authentication requirement, but no exclusions or comparisons.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavioral traits. It fails to explain what 'most recent' means (acquisition date vs. processing date), which satellite platforms are included (e.g., Landsat 8/9), or what happens when no scene is found. The output format is also unspecified.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the core purpose. However, it is slightly too brief given the tool's complexity and lack of annotations, missing some important context that would not be wasteful to include.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the 3 parameters, the absence of output schema, and many sibling tools, the description is insufficient. It does not specify the return format (e.g., a scene ID or metadata), temporal interpretation of 'most recent', or any limitations like scene availability. An agent would lack key information for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description does not add any meaning beyond the schema's parameter descriptions (lat, lng, max_cloud). For example, it does not explain how max_cloud filters scenes or that the tool returns the scene with the lowest cloud cover within the limit.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Find' and the resource 'most recent Landsat scene for a location', which precisely identifies the tool's function. It distinguishes itself from sibling tools like landsat_search (general search) and landsat_timeline (temporal patterns) by focusing on the single most recent scene.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you need the latest scene, but it does not explicitly state when not to use it or mention alternatives. There is no guidance on using landsat_search for more specific queries or landsat_timeline for temporal trends, leaving the agent to infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must fully disclose behavior. It mentions 'named features' and radius search but omits details like API requirements, rate limits, or the structure of results. The description is too terse for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, well-structured sentence that communicates the core functionality without excess. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (3 parameters, no output schema), the description is adequate but lacks context about return format, pagination, or what qualifies as a 'named feature'. Could be slightly more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters are well-documented there. The description adds the concept of 'named features' which clarifies the scope of results, but does not add new parameter meanings beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Identify what is at a given coordinate' with a specific action (identify) and resource (features within a radius). It distinguishes from sibling tools like osm_query or osm_buildings by focusing on radial search for named features.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (when you need to know features at a point) but offers no explicit guidance on when not to use it or alternatives. Among many OSM siblings, no exclusions or comparison is provided, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must shoulder the burden of behavioral disclosure. It only says 'find' without explaining return format, data source, limits, or whether the operation is read-only. This is insufficient for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no fluff. However, it sacrifices depth for brevity. It could include more useful information without significant length increase.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity, the description is minimal but lacks completeness. It does not explain output structure, pagination, or any limitations. Without annotations or output schema, more context is needed for reliable agent usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description does not add any additional meaning beyond the schema; the bounding box context is already implied by the parameter names and descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool finds roads, bridges, and railways within a bounding box. It uses a specific verb ('find') and resource ('roads, bridges, and railways'), and distinguishes itself from sibling tools like osm_buildings and osm_water.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The description implies usage for infrastructure queries but does not mention exclusions or compare to other OSM tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It discloses the action ('Find') and scope ('in a bounding box') but omits details like output format, data source, rate limits, or any side effects. Adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence of 12 words, directly stating the tool's purpose and scope. No filler or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the core functionality but lacks details about return values, data source, or how it relates to similar tools (mil_bases, osm_airports). Given no output schema and no annotations, the description is minimally adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All 4 parameters are fully described in the schema (east, west, north, south as longitudes/latitudes). The description adds no further parameter-level meaning beyond the bounding box context, which is already implicit.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Find military facilities...' with specific examples (bases, airfields, barracks, etc.), making the purpose clear. However, it does not explicitly differentiate from sibling tools like mil_bases, which could cause confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., mil_bases, osm_airports). The description simply states what it does without providing context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavior. It fails to mention whether the tool is read-only, what is returned, any rate limits, or that it queries OpenStreetMap data. This is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, clear sentence that is front-loaded and contains no unnecessary words. It is appropriately sized for a straightforward spatial query tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple bounding box query tool with no output schema, the description is adequate but does not explain the return format (e.g., geometry, properties) or any limitations. It could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all four parameters. The description adds no extra meaning beyond 'in a bounding box,' which is implicit from the parameters. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool finds water bodies, rivers, streams, and dams within a bounding box, using a specific verb and resource. It distinguishes from sibling OSM tools that focus on other features (e.g., osm_buildings, osm_industrial).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like change_water or osm_query. The description only states what it does, not when to choose it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It implies a read operation ('reference') but does not disclose output format, data freshness, or any behavioral constraints. The description is too minimal to be transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one sentence of 13 words, front-loading the core purpose without extraneous information. Every word is necessary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one parameter and no output schema, the description is adequate but lacks details on what the response contains (e.g., specific age groups, percentages). More completeness would improve usability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single parameter 'country' described as 'Country name or ISO code'. The description adds no new semantic meaning beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides population age structure for a country, specifying it as a reference for demographic and intelligence analysis. It distinguishes from sibling tools like pop_density and pop_growth by focusing on age groups.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives or when not to use it. The context signals list many sibling tools, but the description does not differentiate usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the basic operation but omits behavioral traits such as return format, result limits, or API dependencies. Consideration of destructive or read-only nature is absent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, front-loading the core functionality. It could be slightly expanded to include key behavioral details without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 6 parameters, no output schema, and no annotations, the description is insufficient. It does not explain what the tool returns, any limits on results, or how bounding box coordinates are interpreted. Sibling tools suggest more detail might be needed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters are already documented. The description adds minimal semantic value beyond 'over a specified time period' (hinting at 'days'). Baseline 3 is appropriate as it does not significantly extend schema information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses specific verb 'Get' and resource 'earthquakes', and specifies the spatial-temporal context ('within a bounding box over a specified time period'), which clearly distinguishes it from siblings like quake_recent or quake_search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for spatial-temporal queries but does not provide explicit guidance on when to use this tool versus alternatives like quake_search or quake_detail. No exclusions or alternatives are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states the action without any behavioral details (e.g., read-only nature, data source, refresh frequency, or output format). Minimal context beyond purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words. It is front-loaded and efficient, though slightly more detail could be added without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain what the tool returns (e.g., boolean, list of sanctions) or behavior. It does not, leaving the agent uncertain about the response format. Simple tool but still incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both parameters described in the schema. The description adds no additional meaning or clarify beyond what the schema already provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks sanctions status for a specific entity or individual, using a specific verb and resource. It distinguishes itself from sibling tools like sanctions_search (for broader search) and sanctions_vessel (for vessels).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for a single entity/individual but does not provide explicit guidance on when to use vs alternatives such as sanctions_search or sanctions_country. No exclusion criteria or context cues are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavior like read-only, pagination, return format, or rate limits. It only states 'Search' without any behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded, no unnecessary words. Efficiently communicates the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple search with one param, the description is minimally adequate. However, it omits any hint of return values or error conditions. Given no output schema, slightly more context would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the only parameter 'query', which has a description matching the tool's purpose. The description adds no new semantics beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches the OFAC SDN sanctions list for a name, entity, or organization. The verb 'Search' and specific resource 'OFAC SDN sanctions list' make the purpose distinct from siblings like sanctions_changes or sanctions_country.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., sanctions_country, sanctions_entity). No mention of scenarios or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states the basic operation without revealing output format, real-time vs historical nature, rate limits, or any side effects. As a read-like operation, it lacks transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that immediately conveys the tool's purpose. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (spatial query with 4 lat/lon parameters), the description is adequate but does not explain return values or pagination. The absence of an output schema places burden on the description, which it does not fully address.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter having clear descriptions (e.g., 'East longitude'). The description adds no additional meaning beyond the schema, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'all vessels in a bounding box area', and the data source 'using AIS data'. This distinguishes it from sibling tools like ship_search (which may filter by name/MMSI) and ship_position (single vessel).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as ship_search or ship_track. There is no mention of when not to use it or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations were provided, so the description must stand alone. It only states the function without disclosing behavioral traits such as whether the position is always available, what happens if no position is found, or if it requires specific permissions. The brevity leaves the agent uninformed about important behaviors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that efficiently conveys the core purpose. There is no unnecessary information, and it is front-loaded with the action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description provides the essential purpose but lacks details about output format (e.g., coordinates, timestamp) or edge cases. It is minimally complete but could be more informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema describes the single parameter 'vessel_id' with the same phrasing ('GFW vessel ID or MMSI'). The description does not add additional semantics beyond what the schema already provides, so a baseline score of 3 is appropriate given 100% schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get last known position for a vessel by GFW vessel ID' clearly states the action (get), the resource (last known position), and the input method (by GFW vessel ID). It distinguishes this tool from siblings like ship_track (which provides a series of positions) and ship_area (which might be area-based).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as ship_track or ship_search. It does not mention any prerequisites or conditions for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description mentions the API source and the read-only nature of the operation. However, it does not disclose potential errors, rate limits, or coordinate system details. Annotations are absent, so the description must carry the full burden.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that conveys the essential information without any extraneous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, but the description does not specify what the response format will be (e.g., elevation in meters). It also lacks details on accuracy or coordinate system, leaving some gaps for a simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides complete descriptions and bounds for both parameters (lat, lng). The description adds no additional meaning beyond the schema, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets elevation at a coordinate using the Open Elevation API. However, it does not distinguish from the sibling tool 'geo_elevation', which may serve a similar purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'geo_elevation' or other terrain tools. The description only states what it does, not when it is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only mentions return structure but lacks disclosure of behavioral traits such as rate limits, data source freshness, or safety implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no unnecessary words, immediately states purpose and output in a clear and efficient manner.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequately covers core concept but lacks detail on output structure (coordinate system, units) given no output schema; sufficient for basic understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter well-described; description adds context about return values but does not significantly enhance parameter understanding beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'generate an elevation profile between two geographic points' with specific verb and resource, distinguishing from single-point elevation tools like terrain_elevation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives like terrain_elevation or terrain_slope; only a generic description of its function.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits like how elevation is sourced (DEM?), assumptions, limitations, or computational details. For a tool with no annotations, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single efficient sentence that front-loads the core action and outputs. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description lists output types (angle, percentage, classification). However, lacks details on format, units, or coordinate system. For a simple tool with 4 parameters, it is adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions (lat/lng, min/max). The description adds 'between two geographic points' but does not add new semantics beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: calculating slope (gradient) between two geographic points, with specific output details (angle in degrees, percentage, terrain classification). It distinguishes from sibling tools like terrain_elevation by specifying 'slope' explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., terrain_elevation, terrain_flood_risk). The description lacks context for selection among many terrain-related siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It mentions considering terrain elevation along the path, but does not specify the algorithm, assumptions (e.g., Earth curvature, atmospheric refraction), or output format. The return value is implied to be a boolean visibility result but not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is direct and front-loaded with the core purpose. However, it could be slightly more concise by removing 'between two points' since that's implied by observer and target.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, so the description should explain the return value (e.g., boolean, percentage, or line-of-sight path). It does not, nor does it mention data source prerequisites or geographic coverage. This leaves the agent uncertain about what the tool returns.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for all 6 parameters, each with clear descriptions including min/max and defaults for heights. The tool description adds no extra meaning beyond what the schema provides, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it performs line-of-sight analysis between two points (observer and target) considering terrain elevation. The verb 'Determines' and specific resource 'line of sight' make the purpose unambiguous, and it distinguishes from siblings like terrain_elevation (point elevation) and terrain_profile (elevation profile).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. It doesn't mention that for simple elevation queries one should use terrain_elevation, or for elevation profiles use terrain_profile. No context for when line-of-sight is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a read-only data retrieval operation by referencing the 'FAO Food Price Index' and 'trends', but it does not explicitly state that no modifications are made. With no annotations, the burden is on the description to confirm safety; it partially meets this but lacks details on data freshness or limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that immediately communicates the tool's domain (FAO Food Price Index) and scope (global commodity trends). Every word is meaningful, and no extraneous information is present.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of parameters, output schema, and annotations, the description is adequate but minimal. It does not explain what the output looks like (e.g., a number, table, or time series) or how it might be used. Sibling tools often have similarly brief descriptions, so it meets minimal expectations but could be more informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the schema is fully covered (100%). Per guidelines, the baseline is 4. The description does not need to add parameter info, and it correctly implies no inputs are required, but it could mention that no filters are available.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides the 'FAO Food Price Index' and 'global food commodity price trends', which distinguishes it from sibling agricultural tools like agri_crop_health that focus on crop conditions rather than prices. However, it lacks specificity on what exactly is returned (e.g., current index value, historical trends).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives. There are no mentioned use cases, prerequisites, or comparisons to other siblings that might offer price data (such as trade or commodity tools). The description is purely factual without contextual advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full burden. It fails to disclose cell size, event types counted, return format, authentication needs, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with key phrase 'Conflict intensity grid map', no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema. Description omits cell size, resolution, data source, and limitations. For a moderate-complexity tool (5 params), it lacks sufficient detail.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all parameters. The description adds context of dividing bounding box into cells, but this only slightly extends schema meaning, earning baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool creates a grid map of conflict intensity by dividing a bounding box into cells and counting events, distinguishing it from siblings like conflict_events (list events) and conflict_fatalities (fatalities).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by the description (spatial intensity analysis), but no explicit when-to-use, when-not-to-use, or alternatives among sibling tools is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description only mentions 'satellite-derived' but fails to disclose other behavioral traits like data freshness, accuracy, or that it is a read-only operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, highly concise with no wasted words, and front-loaded with the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple coordinate-based lookup, the description covers the key outputs (list of pollutants) and source (satellite), though lacks details on global coverage or data availability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters lat and lng are fully described in the schema (100% coverage); description adds no extra meaning beyond 'at a coordinate', so baseline score applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves satellite-derived air pollution data for specific pollutants (NO2, SO2, CO, PM2.5, ozone) at a given coordinate, distinguishing it from broader tools like atmosphere_air_quality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, such as atmosphere_air_quality, or any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must fully disclose behavior. It mentions data recency limit and sensor type but omits other aspects like return format, pagination, or rate limits. Insufficient for a data retrieval tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with purpose and key constraints. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite full schema coverage and no output schema, the description fails to explain what the tool returns (e.g., point data, summary). This leaves uncertainty, especially with many similar FIRMS siblings.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, providing baseline 3. Description rephrases parameters without adding new semantic meaning (e.g., coordinate format, date format). No extra value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb (retrieve), resource (historical fire detection data from NASA FIRMS), and scope (specific date and bounding box). Distinguishes from sibling FIRMS tools like firms_latest or firms_active_point by specifying historical data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Includes a condition (limited to recent 60 days) but does not explicitly guide when to use this tool over alternatives like firms_latest or firms_active_point. The context is implied but not directive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description implies read-only operation but does not disclose data freshness, rate limits, or any behavioral constraints beyond the boolean 'Get'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no wasted words. Front-loaded with verb and resource, delivering purpose instantly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one required parameter and no output schema, the description sufficiently states inputs and outputs (camp locations and population data). Minor gap: no mention of response structure or pagination, but adequate for straightforward query.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with one parameter 'country' described as 'Country name or ISO code'. Description adds no extra semantic beyond the schema, meeting baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb 'Get' and resource 'refugee camp locations and population data from UNHCR', distinctly specifies the scope (camp-specific) compared to sibling tools like humanitarian_displacement or humanitarian_reports.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., humanitarian_displacement, humanitarian_crises). Does not specify prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses a read operation ('get') without side effects, but does not mention response format, error conditions, or rate limits. For a simple retrieval tool, this is minimally adequate but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One short sentence, fully front-loaded, no filler words. Every part of the description is essential and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, but the description does not clarify what 'detailed metadata' includes. A user cannot infer the returned fields or structure without additional documentation. Incomplete for a metadata retrieval tool intended for programmatic use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with the single 'entity_id' parameter already documented with an example. The description adds only 'by entity ID', which is redundant. No additional semantic value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get') and resource ('detailed metadata for a Landsat scene') and uniquely identifies the input method ('by entity ID'). It clearly distinguishes from sibling tools like landsat_search (which lists scenes) and sentinel_metadata (which is for Sentinel data).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as landsat_search for finding scenes or landsat_bands for spectral data. The description only states the function without any context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states that the tool retrieves scene availability; it does not mention whether the output is a list of years, any constraints like cloud cover, or whether the data is cumulative from 1972. For a tool with no annotations, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is extremely concise and front-loaded with the primary purpose. Every word adds value, with no extraneous details. It is appropriately sized and structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters, no output schema, and no annotations, the description is too sparse. It does not explain what 'scene availability' means (e.g., a timeline of dates, counts per year), how to interpret the output, or any constraints like start_year must be 1972 or later. A more complete description would include the expected return structure and any limitations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All four parameters have descriptions in the input schema (100% coverage). The description adds no additional meaning beyond what the schema provides. It mentions 'for a location,' which is already covered by the required lat/lng parameters. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets Landsat scene availability for a location, with historical coverage since 1972. This distinguishes it from sibling tools like landsat_search (which searches for specific scenes) and landsat_latest (which returns the most recent scenes). The verb 'Get' and resource 'Landsat scene availability' are specific and informative.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for checking historical coverage at a location, but it does not explicitly state when to use this tool vs alternatives such as landsat_search or sentinel_timeline. No exclusion criteria or prerequisites are mentioned. The usage context is clear but guidance on alternatives is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for disclosing behavioral traits. It only states the basic purpose without mentioning data sources, update frequency, rate limits, or limitations (e.g., geographical coverage, reliance on ADS-B). Critical behavioral context is missing for a tool returning live data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that conveys the core purpose without any extraneous words. Every part of the sentence adds value, making it highly concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of live military aircraft tracking and the absence of an output schema, the description is too minimal. It does not explain what the tool returns (e.g., list of aircraft, positions, timestamps) or how the bounding box filtering works in practice. For a data-fetching tool, this completeness is insufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage, with each parameter descriptively labeled (e.g., 'East longitude'). The tool description adds the bounding box concept but does not introduce new semantic details beyond the schema. The description is adequate but does not enhance parameter understanding beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('track live military aircraft'), the spatial context ('bounding box'), and the method ('filtering ICAO24 hex ranges assigned to military operators'). It effectively distinguishes the tool from siblings like 'aircraft_live' and 'mil_activity' by specifying its unique focus on military aircraft via ICAO hex ranges.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for tracking military aircraft within a bounding box but does not provide explicit guidance on when to use this tool versus alternatives such as 'aircraft_military' or 'aircraft_live'. No exclusions or when-not-to-use cases are mentioned, making it adequate but lacking clear differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present. The description does not explain what the tool returns (image, numeric difference?), the area of analysis (point vs. region), or any assumptions (e.g., subtracts radiance). Essential behavioral details are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with a useful dash-separated elaboration. No superfluous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 4 required parameters, no output schema, and no annotations, the description leaves out critical context like output format (image vs. value), area scope, and comparison method. Incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with basic parameter descriptions (lat, lng, date format). The tool description adds no extra meaning beyond the schema. Baseline score applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool compares night light levels between two dates, with specific use cases (power outages, urban growth, conflict damage). It distinguishes from siblings like nightlights_anomaly or nightlights_timeseries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides use cases but does not explicitly compare with sibling tools or state when to prefer this tool over alternatives. Guidance is implied but not direct.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It mentions 'monthly radiance trends' but omits details like data source (VIIRS), update frequency, output format, or limitations. The schema indirectly reveals start year minimum 2012, but the description does not elaborate on behavioral traits beyond a high-level purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the tool's purpose. Every word serves a function, with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is incomplete for a tool without an output schema. It does not describe what the tool returns (e.g., an array of monthly values), the data source, or any constraints. Given the tool's complexity (4 parameters, point-based time series), more detail is needed to be self-sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% so baseline is 3. The description adds no parameter-specific insight beyond the schema; it does not clarify the role of lat/lng or start/end year in generating the time series.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides 'Night light time series analysis — monthly radiance trends' for monitoring urbanization or conflict, using a specific verb ('analysis') and resource ('night light time series'), distinguishing it from siblings like nightlights_anomaly or nightlights_compare.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for monitoring urbanization or conflict but does not explicitly guide when to use this tool over other nightlight tools (e.g., nightlights_anomaly) or provide any restrictions or alternatives. Usage is derived from context, not direct guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description does not mention read-only behavior, side effects, or authentication. Implies safe query but insufficient disclosure for an AI agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise and front-loaded with purpose, but could include more useful context without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks output schema, description mentions return type but not structure. No behavioral details. Adequate but incomplete for a custom query tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, both parameters well-described in schema. Description adds minimal extra meaning beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool runs custom Overpass QL queries against OpenStreetMap data and returns GeoJSON-like elements. Distinguishes from sibling tools that perform specific queries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Does not explicitly state when to use this tool over alternatives. While siblings suggest specific queries, no guidance on when a custom query is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description does not disclose what constitutes 'recent', the format of changes, or any behavioral traits beyond the minimal verb. The agent gets no insight into output or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, front-loaded, no wasted words. Efficient and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no annotations, and no description of return format or constraints. For a tool that presumably returns a list of changes, more detail is needed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no parameters and schema coverage is 100% (empty). Description adds no parameter details because none exist, which is acceptable. Baseline for zero parameters is baseline 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'Check' and the resource 'recent changes to the OFAC sanctions list', which is distinct from sibling tools like sanctions_entity and sanctions_search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, nor any prerequisites or restrictions. The description implies usage for monitoring updates but lacks explicit direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It states it 'checks' but does not disclose whether the operation is read-only, what the response format is, or any limitations (e.g., real-time vs cached). Minimal behavioral context beyond the basic purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no unnecessary words. It front-loads the core action and resource, achieving high conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description lacks completeness. It does not hint at the return value (e.g., boolean, list of sanctions), pagination, or error conditions. For a simple check tool, more context is needed for reliable invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single parameter 'identifier'. The description adds 'by IMO number or vessel name', which aligns with the schema description. No additional semantics or constraints are provided beyond what the schema already conveys.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Check', the resource 'vessel', and the method 'by IMO number or vessel name'. It distinctly separates from sibling tools like sanctions_entity or sanctions_search by focusing specifically on vessels.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when checking a specific vessel, but does not provide explicit guidance on when to use this tool versus siblings like sanctions_search. No when-not-to-use or alternative recommendations are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full behavioral disclosure burden. It only repeats what parameters indicate (search by location, date, cloud cover) without mentioning return format, pagination, rate limits, or whether it's read-only.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 12 words, front-loading the key action and resource. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 6-parameter tool without output schema, the description lacks important context about what results look like, pagination, coordinate system, or how to handle limits. More completeness is needed for effective agent usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so all parameters already have descriptions. The description adds minimal context by naming the categories (location, date range, cloud cover) but does not explain parameter specifics beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (Search), resource (Sentinel-2 satellite imagery), and filtering criteria (location, date range, cloud cover). It distinguishes this tool from siblings like sentinel_latest or sentinel_metadata, which have more specific purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context (search by criteria) but does not explicitly state when to use this tool vs alternatives like landsat_search or planet_search, nor does it mention prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description lacks behavioral details such as data source, update frequency, or limitations. Only the basic purpose is stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, concise and to the point. No fluff, but could be slightly more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description leaves ambiguity about what is returned. Adequate for a simple tool but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents the group parameter with examples. The tool description does not add additional meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'track' and resource 'space debris objects from known fragmentation events'. It distinguishes from sibling tools like space_satellites and space_starlink by focusing on debris from breakups.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not statements. The purpose implies usage, but no guidance on alternatives among sibling tools (e.g., space_satellites for operational satellites).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of disclosure. It does not mention read-only nature, data freshness, limitations, or the structure of the returned data. Only the basic action is stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with no unnecessary words. It is efficient and front-loaded with essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no annotations. The description lacks details about what TLE data includes (e.g., two lines of orbital elements), whether data is current, or any error conditions. For a simple tool, more context would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds no extra meaning beyond mapping 'norad_id' to NORAD catalog number, which is already in the schema description. Baseline 3 is correct.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets TLE orbital data for a satellite using a NORAD catalog number. It uses a specific verb 'Get' and resource 'TLE orbital data', and distinguishes from sibling tools that handle other space-related tasks (e.g., passes, debris, satellites lists).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like space_passes or space_satellites. However, the purpose is self-explanatory for looking up orbital elements, so a mid-range score is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the calculation but does not disclose any behavioral traits such as data source, update frequency, limitations, or that it is a read operation. Minimal disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that is front-loaded. It could be slightly more informative but is not verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and absence of output schema or annotations, the description provides the core functionality but lacks details on output format, edge cases, or data origin. Adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter described, so baseline is 3. The tool description does not add extra meaning beyond the schema; it only repeats the parameters' existence.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Calculate' and the resource 'trade balance between two countries' with the formula 'exports minus imports'. It distinguishes from sibling tools like trade_flow, trade_commodity, etc., by specifying the exact metric.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for calculating bilateral trade balance but does not provide explicit guidance on when to use this tool versus alternatives like trade_flow or trade_timeseries. No exclusions or context are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only states the basic function without detailing data source, units, aggregation method, or limitations like historical coverage or update frequency. This lack of transparency could lead to misuse.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no unnecessary words. It front-loads the key action and resource, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 required parameters and no output schema, the description is too brief. It fails to explain the return format (e.g., a list of years and volumes), data granularity, or any assumptions about the time series. Users are left with incomplete information to assess suitability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds context by explaining that the tool covers 'a country pair over multiple years,' which maps to the required parameters (reporter, partner, start_year, end_year). However, it does not clarify what 'trade volume' means (e.g., exports, imports, total) or provide additional semantic detail beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get trade volume time series for a country pair over multiple years.' It uses a specific verb ('Get') and resource ('trade volume time series'), and distinguishes from sibling tools like trade_balance, trade_commodity, and trade_flow by specifying the time series aspect.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving time series data but provides no explicit guidance on when to use this tool versus alternatives such as trade_balance or trade_commodity. No mention of prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Get recent arrivals' but fails to define 'recent', specify the default time range, clarify if results are real-time, or describe what happens when no arrivals are found. This is minimal for a read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, front-loaded with the verb and resource, and contains no superfluous words. Every part earns its place with high efficiency.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with 3 parameters and no output schema, the description is minimally complete. However, it lacks explanation of the term 'recent', default time ranges, and the existence of optional begin/end parameters, which would help an agent understand tool capabilities fully.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage for parameter descriptions, so the baseline is 3. The description adds no additional meaning beyond mentioning 'ICAO code' for the airport parameter, which matches the schema. No extra context is provided for begin/end parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'recent arrivals', and the key parameter 'by ICAO code'. It is distinct from sibling tools like aircraft_departures (departures vs arrivals) and aircraft_flights (which may be both directions).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving arrivals at a specific airport but does not provide explicit context on when to use this tool vs alternatives (e.g., aircraft_departures for departures) or any exclusion criteria. It does not mention the time range defaults or notes on how to adjust it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so description must carry the burden. It correctly indicates a read operation but does not disclose rate limits, required permissions, or detailed output structure. The mention of cumulative distance adds some value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, 10 words, front-loaded with key information. No wasted words or redundant phrases.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (one required param, no output schema). The description hints at return data (waypoints, distance) but does not specify format, pagination, or limits. Adequate for a straightforward tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with the icao24 parameter already described in the schema. The description adds no extra parameter-level information, so it meets baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (get), resource (flight waypoints), and adds specific calculation (cumulative distance). This distinguishes it from sibling tools like aircraft_track or aircraft_flights.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool over alternatives such as aircraft_track or aircraft_flights. The description does not indicate conditions or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It states 'current' implying real-time data but does not disclose latency, caching, or any side effects. Minimal behavioral context is given beyond the obvious.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence (12 words) with no redundant information. It is well front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple query tool with no output schema, the description mentions 'risk classification' hinting at output but does not detail the response structure. It is adequate but could specify output format or risk categories.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions for lat and lng. The description adds no extra parameter information beyond the schema, meeting the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'current UV index', and the scope 'at a coordinate with risk classification'. It is distinct from sibling tools like atmosphere_air_quality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The description implies usage for UV index queries but does not provide exclusions or mention sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only states that it detects and lists, but does not describe whether it returns current or historical measurements, if there are any rate limits, authentication needs, or what happens if no measurements are found. The description is too minimal for a tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that immediately conveys the tool's purpose. It is front-loaded and concise, with no extraneous words. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has two simple parameters and no output schema. While the description explains the purpose, it lacks detail on the return format (e.g., structure of the list, fields included) and does not mention any limitations (e.g., data recency, geographic coverage). It is minimally complete but could benefit from more context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for both parameters (country_code and limit). The tool description does not add any additional context beyond what the schema already provides, so it meets the baseline expectation for this dimension.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool detects internet censorship using OONI measurements and lists blocked websites and censorship methods. The verb 'detect' and the resource 'internet censorship' are specific, and the mention of listing differentiates it from sibling tools like 'cyber_connectivity' or 'cyber_outage'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for getting censorship data for a country, but it does not explicitly state when to use it versus alternatives (e.g., 'cyber_outage' for outages, 'cyber_connectivity' for connectivity status). There is no mention of when not to use or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only states the basic action without disclosing any behavioral traits such as rate limits, authentication requirements, or result structure. This is a gap for a simple tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that immediately conveys the core action and data source. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one param, no output schema, no annotations), the description is minimally adequate. However, it could benefit from adding context about the output format or typical usage patterns to fully serve an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with one parameter 'country' described as '2-letter ISO country code'. The description adds no extra meaning beyond what the schema provides, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Find'), the resource ('Internet Exchange Points'), and the data source ('using PeeringDB'). It uniquely identifies the tool's purpose among siblings like cyber_cable_landing and cyber_ip_locate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool over alternatives. The description implies usage when IXPs are needed for a country, but does not mention exclusions or sibling differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It does not disclose whether data is real-time, historical, or forecast; any units or output format; or authentication needs. Only states functionality without behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no wasted words. Front-loaded with verb and key information. Highly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description lacks detail on return format, units, and potential time parameters. However, for a simple point query tool, it adequately covers core purpose. Could be improved with additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions for lat and lng (including 'ocean location'). Tool description adds little beyond calling it a 'coordinate'. Baseline 3 is appropriate as parameters are already well-documented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it retrieves sea surface temperature at a coordinate using Open-Meteo marine data. The verb 'Get' and specific resource 'sea surface temperature (SST)' make purpose unambiguous. Distinguished from sibling 'ocean_sst_anomaly' which is for anomalies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes using it to get SST at a coordinate, implying use for a single point, but does not specify when to use versus alternatives like ocean_buoy_data or ocean_chlorophyll, nor when not to use. No explicit guidance on context or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full responsibility. It mentions retrieving data but does not disclose read-only nature, authentication requirements, data freshness, or rate limits. Important behavioral context is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with the verb 'Retrieve' front-loaded. Every sentence adds value without waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description explains purpose and ordering but does not clarify output format (e.g., GeoJSON) or any pagination behavior. Given no output schema, this is a moderate gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so both parameters (limit, source) have descriptions. The description adds no additional meaning beyond the schema's parameter descriptions, achieving only baseline value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves the latest global fire detections from NASA FIRMS, sorted newest first. This distinguishes it from sibling tools like firms_history (historical) and firms_active_area (area-specific).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for monitoring breaking wildfires but does not explicitly state when not to use or mention alternative tools like firms_history or firms_active_country. It provides context but lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral traits. It reveals the use of Nominatim (external service) and that it returns a full address, but it omits critical details: rate limits, data sources, accuracy, error handling for invalid coordinates, and output format specifics. Given the lack of annotations, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (two sentences), front-loaded with the main purpose, and contains no unnecessary words. It effectively communicates the core functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should elaborate on the return structure. It vaguely says 'Returns the full address with structured components' without specifying the fields (e.g., road, city, country). For a tool with many siblings, this lack of detail could lead to incomplete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage for both parameters (lat and lng) with clear range descriptions. The description adds no additional semantics beyond what the schema already provides. Thus, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Reverse geocoding: convert latitude/longitude coordinates to a human-readable address using Nominatim.' It specifies the verb (convert), resource (coordinates to address), and service (Nominatim). This distinguishes it from sibling tools like geo_forward.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when coordinates are available and an address is needed, but it does not provide explicit guidance on when not to use it or mention explicit alternatives (e.g., 'Use geo_forward for address to coordinates'). With sibling tools like geo_forward present, more explicit differentiation would help.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description lacks behavioral details such as read-only safety, authentication requirements, rate limits, or what happens if no results are found. The description only states the basic function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the core action and resource. Every word is necessary, and there is no extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple bounding box query with 4 well-defined parameters and no output schema, the description is minimally adequate. However, it does not mention the return format or behavior on empty results, which would be helpful for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for all four parameters (east, west, north, south) with min/max and type. The description does not add any additional meaning beyond what is in the schema, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Find', the specific resource 'submarine cable landing points', and the spatial constraint 'in a bounding box'. This distinguishes it from related sibling tools like cyber_cable_landing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when querying submarine cable landing points by bounding box, but does not explicitly state when not to use it or mention alternative tools. Sibling context suggests alternatives, but no guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. It discloses input (bbox) but lacks details on output format, pagination, rate limits, or any mutational effects. Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with key action and resource. No superfluous words. Maximum conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool is simple, but without output schema or annotations, description is minimal. Agent could benefit from knowing output type (e.g., GeoJSON) or limits. Adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for each coordinate parameter. Description adds context that the tool searches for renewable installations, but does not enhance parameter semantics beyond what schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool finds renewable energy installations (wind turbines, solar farms) within a bounding box, using specific verb and resource. It distinguishes from sibling infrastructure tools like infra_power or infra_cables.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies usage for locating renewable energy in a geographical area but provides no explicit guidance on when to use vs alternatives, no exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the core function without disclosing behaviors like authentication, rate limits, valid entity ID format, or error responses. The tool's simplicity reduces need, but transparency is lacking.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no unnecessary words. Every word contributes to the purpose, achieving maximum conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one parameter and no output schema, the description is minimally adequate but lacks details about the return URL format or any constraints. It could mention that the URL is for a thumbnail image, but as is, it's functional but sparse.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (entity_id described as 'Landsat entity ID'). The description adds no additional meaning beyond the schema. Baseline 3 is appropriate as schema already documents the parameter adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get browse/thumbnail URL for a Landsat scene.' It specifies the action (Get) and the specific resource (browse/thumbnail URL), effectively distinguishing it from sibling Landsat tools like landsat_bands, landsat_download_url, and landsat_metadata.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is provided. The purpose implies it for fetching thumbnails, but it does not contrast with alternatives (e.g., landsat_download_url for actual data, landsat_metadata for metadata). Usage context is implied but not clarified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description lacks details on data sources, update frequency, limitations, result format, or constraints beyond the bounding box. Minimal behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, concise, front-loaded with verb and resource. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple spatial query tool, the description explains input but not output format or any other context. No output schema exists, so more detail would be beneficial, but it is minimally viable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for each parameter. The description adds minimal value beyond stating the bounding box, which is already implied by parameter names. Adequate, not enhanced.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Find' and the resource 'restricted, danger, prohibited, and military airspace zones', with spatial context 'in a bounding box'. This distinguishes it from sibling tools like mil_aircraft or mil_bases.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when needing those airspace zones within a bounding box, but does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It states the tool 'constructs a URL', but does not mention side effects, authentication, rate limits, or whether the URL returns a tile image directly. The behavior is minimally transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no extraneous words. The purpose is front-loaded in the first sentence, and the second provides essential context and examples. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, so the description should explain what the return value is (a URL string) and how to use it. It mentions tiles can be viewed in map clients, implying the URL is usable, but it does not specify the output structure or any required authentication. For a URL-construction tool, this is adequate but lacks some details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all five parameters. The description adds minor context (examples of common layers, date format) but does not significantly enhance meaning beyond the schema. Hence a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool constructs a NASA GIBS WMTS tile URL for a specific layer, date, and tile coordinate. It includes a list of common layers, which helps the agent understand the scope and distinguish this tool from unrelated siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides context (near-real-time and archival satellite imagery as map tiles) and states tiles can be viewed or downloaded, implying usage for map visualization. However, it does not explicitly state when to use this tool versus alternatives or provide exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only mentions authentication but does not reveal whether the URL is time-limited, whether the product must be previously searched, or any other side effects or safety considerations. For a simple read operation, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences, no unnecessary words, and front-loads the action. Every sentence serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one parameter, no output schema), the description is minimally adequate. However, it lacks details about the response format or the nature of the URL, and does not reference siblings like landsat_download_url for context. It could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the baseline is 3. The description adds no additional meaning beyond the schema for the single parameter 'product_id', which is already clearly described as 'Copernicus product ID'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Get download URL for a Sentinel-2 product.' It uses a specific verb ('Get') and resource ('download URL'), and distinguishes itself from sibling Sentinel tools like sentinel_search or sentinel_metadata.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions a prerequisite ('Requires Copernicus authentication') but does not provide guidance on when to use this tool versus alternatives, nor does it specify when not to use it. The usage context is implied but not fully elaborated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It states it retrieves dates but does not disclose behavioral traits such as data freshness, rate limits, authentication needs, or what 'available' means. It adds minimal context beyond the input schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words. It front-loads the verb and resource, making it immediately scannable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having 3 parameters, the description is very brief. It does not explain output format (e.g., list of dates with metadata), usage context, or how it differs from sentinel_latest. For a simple tool this might suffice, but more completeness would help.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (all three parameters have descriptions). The tool description does not add new meaning beyond the schema; it merely restates the context. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'available Sentinel-2 image dates' for a location over a specific time period ('past year'). It distinguishes itself from siblings like sentinel_search (search for specific images) and landsat_timeline (Landsat equivalent) by focusing on dates rather than image retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is provided. The description implies usage when needing a timeline of image availability, but does not mention alternatives or exclusion criteria among the many sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the search action and source, lacking details about behavioral traits like read-only nature, return format, authentication, or rate limits. The description does not disclose what happens during or after the search.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no wasted words. It is front-loaded with the action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequately complete for a simple search tool with one parameter, but it lacks details about the output format or how results relate to sibling tools, which would be helpful given no output schema is provided.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of parameters with a description matching the tool description. The description adds no new semantic meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for vessels by name, MMSI, or IMO number using Global Fishing Watch. It uses a specific verb 'Search' and identifies the resource and identifiers, distinguishing it from other ship tools like ship_position or ship_track.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you have a vessel identifier, but provides no explicit guidance on when to use this tool versus alternatives such as ship_fishing or ship_port_visits. No exclusions or context are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility for behavioral disclosure. It mentions querying a 'grid of elevation points' but omits details about return format, data source, performance, or any limitations. The agent is left guessing what the output will be.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of two sentences with no redundant wording. The first sentence states the core action, and the second adds context for usage. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description should ideally explain what the tool returns (e.g., coordinates and elevation values for max/min). It does not, leaving the agent partially uninformed. However, it adequately explains the method and purpose, so it is adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter already described in the input schema. The description's mention of 'bounding box area' and 'grid of elevation points' does not add new meaning beyond the schema definitions, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Find the highest and lowest points in a bounding box area by querying a grid of elevation points.' It uses a specific verb ('Find') and resource ('highest and lowest points'), and the mention of 'terrain prominence and relief analysis' distinguishes it from sibling tools like terrain_elevation or terrain_profile.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description identifies a use case ('terrain prominence and relief analysis') but does not provide explicit when-to-use or when-not-to-use guidance compared to alternatives. The context is clear but lacks exclusions or direct comparisons to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavioral traits. It states what data is returned but does not mention side effects, authorization requirements, rate limits, data freshness, or response format. This is insufficient transparency for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the purpose and lists key outputs. Every word contributes, and it avoids redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with no output schema and no annotations, the description lists returned variables but omits units, format, and potential constraints (e.g., API key requirements). It is adequate but not fully complete for an agent to use without additional assumptions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters (lat, lng). The description adds no extra meaning beyond 'at a coordinate', so it meets the baseline but does not enhance understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses specific verbs and resources ('Get current weather conditions') and lists included variables, distinguishing it from siblings like weather_forecast (future) and weather_historical (past). It is unambiguous about the tool's function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for current conditions but provides no explicit guidance on when to use alternatives (e.g., weather_forecast for predictions) or when not to use this tool. The context is clear but lacks exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full disclosure burden. It lists return data fields but omits potential behavioral traits such as rate limits, update frequency, authentication needs, or handling of invalid bounding boxes. It is clear that this is a read operation, but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the core action and then lists included fields. Every phrase adds value; no unnecessary words. Could be slightly more concise but is already efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description partially compensates by listing return fields. However, it does not specify output format (e.g., JSON array of objects), pagination, or error handling. For a tool with 4 required parameters and no output schema, this is adequate but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents parameter meanings (e.g., 'East longitude'). The description adds no extra semantic details beyond what the schema provides (e.g., value ranges, ordering, or units). Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get), the resource (live aircraft positions), the scope (within a bounding box), and lists specific return fields (position, altitude, speed, heading, origin country). It distinguishes itself from sibling tools like aircraft_track or aircraft_arrivals by focusing on live positions in a bounding box.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for retrieving live aircraft in a geographic area, but provides no explicit guidance on when to use this over alternatives like aircraft_search, aircraft_track, or aircraft_flights. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description partially carries behavioral disclosure. It reveals 'currently airborne' and 'partial match' but omits return format, pagination, or limitations. Additional context would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and front-loaded with the verb and resource. It is efficient but could be slightly richer without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool with full schema coverage and no output schema, the description provides adequate purpose and parameter info. However, missing output description and context on data freshness limits completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description repeats the parameter's description (case-insensitive, partial match) already in schema, adding no new meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for currently airborne aircraft by callsign with partial match support. It distinguishes from sibling tools like aircraft_flights, aircraft_live, and aircraft_track by specifying 'currently airborne' and 'callsign search'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for real-time airborne queries but provides no explicit guidance on when to use this tool versus alternatives like aircraft_flights or aircraft_track. No when-not-to-use or alternative mentions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description indicates it is a computation tool with no destructive effects. However, it does not disclose what 'overall landscape change assessment' means, nor any input constraints (e.g., reflectance format). It adequately conveys the basic behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, information-dense sentence lists all computed indices and the dual-date nature. No unnecessary words or repetition. Perfectly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description omits the output format and any prerequisites (e.g., correct band order, scaling). With 10 required parameters and no output schema, the tool's return value ('overall landscape change assessment') is vague, leaving the agent uncertain about what to expect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with each parameter described as a band reflectance for a specific date. The description adds no new meaning beyond grouping parameters into 'two dates' and listing indices, which is already implied. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool computes five spectral indices (NDVI, NDWI, NDBI, NBR, BSI) from two dates and produces an overall change assessment. This distinguishes it from single-index siblings like change_vegetation or spectral_ndvi.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for multi-index change analysis, but does not explicitly guide when to choose this tool over individual index tools (e.g., spectral_ndvi) or other change tools. No exclusions or alternatives are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description reveals that it computes NDWI and interprets the difference, but it does not specify what the output looks like (e.g., thresholded change areas, continuous values) or disclose any side effects, rate limits, or required permissions. Moderately transparent but lacks detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that front-load the core purpose and method. No superfluous information, every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool lacks an output schema, but the description only vaguely mentions 'interprets the difference' without describing the output format or thresholds. It also omits prerequisites (e.g., atmospheric correction) and context about how the change interpretation is performed, leaving the agent underinformed for a reasonably complex operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents each parameter's meaning (e.g., 'Green band reflectance for the earlier date'). The description adds the context of NDWI but no additional semantic value beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it detects water body changes using NDWI, specifies the computation (NDWI for two dates from Green and NIR bands), and distinguishes itself from siblings like change_vegetation (which likely uses NDVI) and spectral_ndwi (which computes single-date NDWI).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for water body change detection over two dates but provides no explicit guidance on when to use it versus alternatives (e.g., change_detect, spectral_ndwi) or when not to use it. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full burden for behavioral disclosure. It describes the output (total fatalities, breakdown by event type, deadliest events) but omits details like data source, update frequency, read-only nature, or limitations. No contradiction with annotations exists, but transparency is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that efficiently conveys the tool's purpose and output. No wasted words, though it could be slightly more informative (e.g., specifying return type). Structure is clean.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should more fully explain the return format. It mentions total fatalities, breakdown by event type, and deadliest events but doesn't clarify whether the output is a list, object, or how data is structured. For a tool with three parameters, this is adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all three parameters (country required, year, limit). The tool description adds information about output but not about parameters themselves. Thus, it does not augment schema meaning, earning baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides conflict fatality statistics with specific outputs: total fatalities, breakdown by event type, and deadliest events. It effectively distinguishes itself from sibling tools like conflict_events (events), conflict_actors (actors), and conflict_hotspots (hotspots) by focusing on fatalities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly suggests usage for fatality statistics but provides no explicit guidance on when to use this tool versus alternatives (e.g., conflict_events). It lacks when-not-to-use conditions or alternative tool references, which would help an AI agent choose correctly among many conflict-related siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only lists the output fields but does not disclose any behavioral traits like rate limits, authentication requirements, or error handling. It implies a read-only operation but does not explicitly state it.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with 7 words, extremely concise and front-loaded with the verb 'Geolocate'. Every word contributes to the purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description adequately lists the return types. It is complete enough for an agent to understand what the tool does and what it returns.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with a single parameter 'ip' already described. The description adds no new details beyond what the schema provides, so it meets the baseline. No additional parameter semantics are contributed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Geolocate an IP address' and lists the types of information returned. It clearly distinguishes this tool from sibling tools like cyber_cable_landing or cyber_censorship, which have different functions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for geolocating an IP but provides no explicit guidance on when to use this tool versus alternatives, such as other cyber tools. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose behavioral details beyond the basic retrieval action. With no annotations, it fails to specify output format, pagination, real-time nature, or edge cases (e.g., empty results). However, the tool is simple, so this is minimally adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. It is concise and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with three parameters and no output schema, the description provides the gist. However, it lacks details on output format, date range limits (days max 365 not stated), and potential data freshness. Adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents each parameter. The description adds 'near a coordinate' and 'recent' which weakly relate to lat/lng and days, but does not add substantive new meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves deforestation alerts (GLAD) near a coordinate, specifying the data source (GLAD) and the subject (deforestation, tree cover loss). It is distinct from sibling tools like env_fire_risk or change_vegetation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is provided. The name and description imply usage for deforestation alerts, but no alternatives or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It describes the return values but does not mention any behavioral traits such as whether the tool is read-only, if there are rate limits, maximum bounding box constraints, or how missing data is handled. This leaves significant gaps for an agent to infer safety and limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first states the main purpose, second lists the specific outputs, and a third provides a use case. No redundant words; every sentence adds value. The structure is front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately enumerates the return values (total fire count, average brightness, FRP, day/night distribution, confidence breakdown). It also provides a use case (wildfire risk assessment). However, it does not mention response format, units, or error behavior, which would enhance completeness for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter described (e.g., lat/lon ranges, days enum). The description adds minimal parameter information beyond the schema, only confirming that 'time period' maps to days and 'geographic area' to bounding box. Baseline 3 is appropriate because schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Compute aggregate fire statistics' and specifies the resource 'for a geographic area over a time period'. It differentiates from sibling firms tools (e.g., firms_active_point, firms_history) by focusing on aggregated statistics rather than individual fire points or historical records.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says 'Useful for wildfire risk assessment and trend analysis', implying appropriate use cases. However, it does not explicitly contrast with alternatives or state when not to use this tool (e.g., for real-time fire tracking use firms_latest). The usage context is implied but not exclusionary.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist; the description implies a read-only operation via 'Get'. It does not discuss rate limits, authentication, or potential errors. For a simple query, the transparency is adequate but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no unnecessary words. The purpose is front-loaded in the first sentence. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately explains the return (elevation in meters and feet). It lacks details on error handling or API usage notes, but for a simple tool, it is mostly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (both lat and lng described). The description adds no additional parameter semantics beyond the schema. It does clarify the output format (meters/feet), but this is not parameter-related.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets elevation for a geographic coordinate, specifies the API source (Open Elevation), and notes the output format (meters and feet). The verb 'Get' and resource 'elevation' are unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like terrain_elevation or other elevation-related siblings. No context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose all behaviors. It states times are in UTC, which is helpful. However, it does not mention edge cases like polar regions (no sunrise/sunset), error handling, or the effect of missing date (defaults to today, as per schema). Basic transparency but incomplete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with key functionality, no redundancy. Every word adds value. Ideal length for a simple calculator tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description adequately covers inputs, outputs, and time zone for a tool with no output schema. It could mention edge cases or return format, but is sufficient for typical use. Lacks only minor details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents parameters. The description adds meaning by listing outputs, but does not enrich parameter understanding (e.g., lat/lng bounds or date format). Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool calculates sun position data and lists specific outputs (sunrise, sunset, solar noon, civil dawn/dusk, day length). This verb+resource combination is distinct from sibling tools like geo_elevation or geo_timezone, making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The description lacks conditions, prerequisites, or mentions of when not to use. While siblings are mostly non-overlapping, there is no proactive direction for the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It does not mention whether the tool is read-only, any rate limits, authorization needs, or return format. The single sentence lacks sufficient transparency for a tool with no structured behavioral hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no unnecessary words. Every element (action, resource, scope) earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple bounding-box query with 4 documented parameters, the description provides essential context about what is found and where. However, it lacks details about the output (e.g., return format, result count), which would be helpful given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the existing parameter descriptions are adequate for basic usage. The tool description adds no additional meaning beyond the schema, so score is baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Find'), the resources ('power plants, substations, and transmission lines'), and the geographic scope ('in a bounding box'). It effectively distinguishes from sibling infrastructure tools that focus on other domains (e.g., energy, cables, pipelines).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives (e.g., infra_energy). The usage is implied by the description (querying power infrastructure), but no when-not or exclusion criteria are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must carry the full burden. It lacks details on output format, pagination, or error behavior. It only states filtering criteria without disclosing what happens with results (e.g., returns list of scenes, metadata, etc.).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words. Front-loads the core action and filtering dimensions. Efficient for an agent to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and many sibling tools, the description is too brief. It does not explain what the search returns (e.g., scene IDs, metadata, browse URLs) or how to interpret results. Lacks completeness for an agent to reliably use without additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% description coverage for all 6 parameters. The description adds value by specifying the satellite family (Landsat 8/9) and unifying the filtering dimensions (location, date range, cloud cover) beyond individual param descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it searches Landsat 8/9 satellite scenes by location, date range, and cloud cover. The verb 'search' and specific satellite identifiers distinguish it from sibling tools like landsat_bands or landsat_metadata.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or alternative guidance. The description implies usage for scene search but does not differentiate from other landsat tools beyond the basic purpose. Agents must infer from tool names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description carries full responsibility for behavioral disclosure. It does not mention query limits, update frequency, potential missing features, or how the data is returned. Only the basic function is described.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words. All necessary information is front-loaded: action, target, scope, source.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple parameter set and no output schema, the description is sufficient for basic understanding. However, it could mention the output format or typical response structure to be fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema covers all 4 parameters with descriptions (south, west, north, east). The description adds 'bounding box' context but does not provide additional details or examples beyond what the schema offers.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action ('Find'), the resources ('military bases, barracks, airfields, ranges, and bunkers'), the geographic scope ('in a bounding box'), and the data source ('using OpenStreetMap data'). It distinguishes itself from sibling tools like 'osm_military' by specifying the types of military features.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The bounding box constraint is implied but there is no mention of prerequisites, limitations, or comparison with similar tools like 'osm_military' or 'geo_bbox'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses that the API returns the closest available image for the given date, which is helpful. However, it does not mention any potential limitations like missing data, rate limits, or authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, directly stating the action and a use case, with no unnecessary words. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool that returns a URL, the description adequately explains the output. The four parameters are fully defined in the schema, and no output schema is needed. Some context about data availability could be added, but the description is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with each parameter described in the schema. The description adds no additional semantic information beyond summarizing the purpose; thus, baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a Landsat 8 natural color satellite imagery URL for a given coordinate and date, which is specific. However, it does not explicitly differentiate from similar sibling tools like landsat_browse or nasa_earth_assets.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions 'useful for visual inspection of a location from space', giving a general use case, but provides no guidance on when not to use the tool or mention of alternatives among the many sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must cover behavior. It indicates a read operation ('Get') and specifies data sources and measurements, but doesn't disclose potential constraints like station validity, data update frequency, or response format. This is adequate for a simple fetch tool but not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that immediately conveys the tool's purpose. It is concise, front-loaded, and contains no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, the description lists expected measurements (wave height, wind, temperature, pressure), giving agents a reasonable understanding of the return data. However, it omits details like time range, units, or how to specify historical/current data, slightly reducing completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter (station) with a description including examples. Schema coverage is 100%, so the description adds little beyond noting the data source. The baseline of 3 is appropriate; no additional semantic value is provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: retrieving ocean buoy measurements (wave height, wind, temperature, pressure) from NOAA NDBC. It uses a specific verb and resource, making it easy to understand. Although it doesn't explicitly differentiate from sibling tools like env_ocean_temp, the specificity of buoy data and listed parameters sets it apart effectively.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., satellite-derived ocean data from env_ocean_temp). It lacks exclusions or context for optimal use, leaving the agent to infer usage from the name and schema.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully bears the burden of disclosure. It indicates a read operation (get data) but does not mention output format, pagination, or any constraints like coordinate validity or bounding box behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that immediately states the verb and resource. It is front-loaded and contains no unnecessary words, making it highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Although no output schema exists, the description hints at the return type ('urban areas and their characteristics'). For a simple query tool with three basic parameters, this provides adequate context, though an example output would be more helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description does not add meaning beyond the schema; it only restates that lat/lng are coordinates and radius_km is for proximity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves urbanization and city data for a given coordinate, specifying 'nearby urban areas and their characteristics.' This clearly distinguishes from sibling tools like pop_density which focus on demographic data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as pop_density or other location-based tools. The description only states what the tool does, not when it is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states a read operation without disclosing potential errors, authentication needs, rate limits, or whether the data is always available. The description does not describe return value format or behavior on invalid input.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 10 words, front-loaded with the core purpose. Every word adds value; no unnecessary detail or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (one parameter, no output schema) and the description adequately outlines the output scope (sanction level, programs, restrictions). It could mention error handling or data availability, but overall it is complete for a basic retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the 'country' parameter with 100% coverage. The description does not add any additional meaning, such as accepted formats, examples, or restrictions beyond what the schema provides. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get'), the resource ('sanctions program summary'), and the scope ('for a country'). It distinguishes from sibling sanctions tools like sanctions_entity or sanctions_vessel by focusing on countries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for getting a country's sanctions summary but does not explicitly mention when to use this tool over alternatives (e.g., sanctions_entity for entities, sanctions_search for broader search). No guidance on prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description only states basic action without disclosing any behavioral traits such as rate limits, permissions, or data availability conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Highly concise one-sentence description with no unnecessary words; front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 3-parameter tool with no output schema, the description adequately covers the basic operation and purpose, though could mention return type.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage with descriptions, so description adds minimal new meaning beyond the schema. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'Get', resource 'vessel movement history (GPS track)', and scope 'over a date range', distinguishing it from sibling tools like 'ship_position' and 'ship_search'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies use for historical track data but does not explicitly state when to use versus alternatives; no exclusions or prerequisites provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description must fully disclose behavioral traits. The description indicates a read operation ('get') with no side effects, which is reasonable. However, it omits details such as data source, update frequency, rate limits, or whether the returned data is aggregated or raw. The minimal transparency is acceptable but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence of 10 words. It conveys the essential information without any filler. Every word earns its place, making it highly efficient for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has only three parameters and no output schema, the description provides a clear enough overview. It lacks details on the output structure or data types, but for a straightforward data retrieval tool, the description is adequately complete without being overly verbose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers all three parameters with descriptions (year, reporter, commodity). The description does not add additional semantic value beyond what the schema already provides, such as clarifying the meaning of 'global' or the format of HS codes. Since schema coverage is 100%, the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get global trade data for a specific commodity (HS code)' clearly states the action (get), the resource (global trade data), and the specific scope (a specific commodity identified by HS code). It effectively distinguishes from sibling tools like trade_balance, trade_flow, trade_partners, and trade_timeseries, which focus on different aspects of trade data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no explicit guidance on when to use this tool versus alternatives. While the purpose is clear, it lacks information on prerequisites, context, or exclusions. The sibling tools are listed but no comparison is offered, leaving the agent to infer the appropriate use case from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It explains the method and output concept (NDVI time series reference) but does not disclose specific behavioral traits like data source freshness, rate limits, or whether the operation is read-only. Basic transparency but lacking depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with 12 words, front-loading the core purpose. No unnecessary words, and every part adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (two parameters, no output schema), the description provides essential information but lacks detail on what the output looks like or any return value structure. Adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with descriptions for lat and lng. The description adds no additional meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'assess', the resource 'crop health', and the method 'NDVI time series reference'. It also mentions linking to satellite vegetation indices, distinguishing it from siblings like agri_drought or spectral_ndvi.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is provided. The purpose is implied from the name and description, but there is no mention of alternatives or contextual conditions for using this tool over similar ones.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description explains the algorithm (compute NBR, classify severity) but does not disclose side effects, classification thresholds, or safety implications (e.g., read-only vs destructive). Some behavioral info is present but incomplete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose, no redundancy. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, yet description does not explain output format or severity classes. Given 4 parameters and a computational task, more detail on expected results would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% description coverage for all parameters. The description adds context by explaining that parameters correspond to pre/post NIR and SWIR bands used in dNBR calculation, which is beyond the schema's field descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool detects fire scar/burn severity using dNBR, with specific mention of NIR and SWIR bands and pre/post dates. This distinguishes it from sibling tools like change_detect or spectral_nbr.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. Does not mention prerequisites like satellite imagery or contexts where this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry full burden. Mentions classification of magnitude beyond mere difference, but doesn't detail thresholds, output structure, or potential side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence conveying all essential information without filler. Highly efficient and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple tool, but lacks detail on classification categories, typical use cases, or guidance relative to specific change tools. No output schema and no annotations increase information burden.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions. Description adds context about date comparison and classification, but doesn't significantly enhance understanding beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it computes difference of any spectral index between two dates and classifies magnitude. Verb 'computes' and specific resource 'change detection of spectral indices' distinguish it from sibling tools like change_burn or change_vegetation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies broad applicability via 'general-purpose', but lacks explicit guidance on when to use this versus specific change tools, no conditions or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions using current weather conditions but does not disclose output format, rate limits, or whether it's read-only. This is adequate but could be more transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words, front-loaded with the primary action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 2 parameters and no output schema, the description provides the basic purpose but lacks information about output format, range, or limitations. It is adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description does not add additional meaning to the parameters beyond what the schema already provides (lat and lng).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool assesses fire risk at a location based on current weather conditions, listing specific factors (temperature, humidity, wind, drought index). This distinguishes it from sibling tools like weather_current or agri_drought.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for fire risk assessment but does not provide explicit guidance on when to use this tool vs alternatives, nor any when-not-to-use conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It mentions returned fields and sensors but omits details like pagination, rate limits, data freshness, or the read-only nature. It does not contradict any annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences deliver the core purpose and key details without extraneous information. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with six parameters and no output schema, the description covers basic functionality but lacks details on result limits, bounding box constraints, or ordering. Adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds context about sensor resolutions (375m vs 1km) and enumerates returned fields, but does not provide additional semantics for coordinates or days beyond what the schema already states.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool queries NASA FIRMS for active fire detections within a bounding box, specifying the returned fields (brightness, confidence, FRP, acquisition time) and supported sensors (VIIRS, MODIS). This distinguishes it from sibling tools like firms_active_country or firms_active_point.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for area-based queries via bounding box but does not explicitly mention when to use alternatives like firms_active_point or firms_active_country. Sensor selection guidance is provided, but no when-not-to-use advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the service (Nominatim) and output fields but omits potential behavioral traits like rate limits, error handling for ambiguous queries, or authentication requirements. Adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences efficiently convey purpose, method, and output. No unnecessary words, but could be slightly more structured (e.g., listing return items). Still commendable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description covers the essential: what it does, how it works, and what it returns. Lacks detail on return format but sufficient for most use cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with the one parameter 'query' already described in schema. The description adds an example but no additional semantics beyond the schema. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool converts an address/place name to coordinates, using Nominatim, and specifies return content (up to 5 results with coordinates, type, importance). It is distinct from sibling geo_reverse (reverse geocoding) and other location tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (forward geocoding) but does not explicitly contrast with alternatives like geo_reverse or give criteria for when not to use. The context with siblings (e.g., geo_reverse) helps, but the description itself lacks explicit usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral transparency. It only states what the tool finds, but does not disclose any behavioral traits such as data sources, update frequency, response format, or limitations. This is insufficient for an agent to fully understand the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that immediately states the tool's purpose and scope. Every word contributes value, with no filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has four required parameters, no output schema, and no annotations, the description is brief. It explains the input and purpose but lacks details about outputs, error handling, or result limits. For a simple bounding box query, this is adequate but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All four parameters (south, west, north, east) are described in the schema with latitude/longitude labels and bounds. The description adds minimal extra meaning by linking them to a bounding box for nuclear facilities. Since schema coverage is 100%, baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool finds nuclear facilities (power plants, research reactors, enrichment sites) within a bounding box. The verb 'find' and specific resource types are clearly communicated, distinguishing it from many sibling tools like mil_bases or mil_aircraft.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates using a bounding box to find nuclear facilities, implying a spatial query. It does not explicitly mention when not to use or list alternative tools, but the context of many sibling tools makes the usage reasonably clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states that it retrieves data without disclosing rate limits, authentication requirements, or the structure of the response. The schema includes a note on max date range, but the description itself adds no behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences that efficiently convey the purpose and key parameters. It is well-structured with the main action first, followed by examples and use cases. No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequate for a simple data retrieval tool, but it lacks details about the output format or what users can expect to receive. With no output schema, some guidance on the response structure would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds significant value beyond the schema by explaining common parameter codes and their meanings (e.g., ALLSKY_SFC_SW_DWN for solar irradiance). It also mentions the default parameters. However, the schema already covers all parameter descriptions, so the baseline is high.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves daily solar and meteorological parameters from NASA POWER for a location and date range. It lists specific parameters like ALLSKY_SFC_SW_DWN, T2M, and WS2M, which distinguishes it from other sibling tools that may focus on different data sources or types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions it is useful for renewable energy assessment and agricultural planning, providing context for when to use it. However, it does not explicitly state when not to use this tool or compare it to alternatives like weather_current or weather_forecast, which could be confused with this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behavioral traits (resolution, coverage, API key requirement) but omits details like pagination, rate limits, or error handling. Without annotations, the description carries full burden, and while adequate, could be more comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise with two sentences, front-loading the purpose and essential requirement. Every word earns its place without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Sufficient for basic understanding but incomplete without output schema or mention of return values. Given the tool's complexity and 7 parameters, more detail on results structure would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the description adds limited value beyond parameter names and types. It provides catalog context but no additional meaning for individual parameters, earning a baseline score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it searches Planet Labs satellite imagery catalog with specific resolution and coverage details, differentiating it from siblings like landsat_search or sentinel_search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Mentions the required API key, providing a necessary usage condition, but lacks explicit guidance on when to use this tool vs alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It implies a read-only retrieval operation, but does not explicitly state non-destructiveness or disclose any behavioral traits beyond the basic functionality.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, clear sentence with no unnecessary words, perfectly sized for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one parameter and no output schema. The description is adequate but does not specify what 'detailed information' includes, leaving some ambiguity about the response format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides a clear description for event_id with an example. The tool description adds no additional meaning beyond what the schema provides, and schema coverage is 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get detailed information about a specific earthquake by USGS event ID', using a specific verb and resource, and distinguishes from sibling tools like quake_recent and quake_search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implicitly indicates use when an event ID is known, but no explicit when-to-use, when-not-to-use, or alternative tools are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description mentions the type of statistics returned but does not disclose other behavioral traits like read-only nature, performance, or any constraints beyond input bounds.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, well-structured, front-loaded with tool purpose, efficiently conveys key information without fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks output schema; description outlines statistics but not format. Adequate for basic understanding but could be more complete regarding return structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions for each parameter (days, bounding box). The description adds 'optional region' which matches the bounding box params but does not provide new semantic value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides 'earthquake statistics' with specifics like magnitude distribution, deepest, strongest, averages, distinguishing it from other quake tools (search, detail, area).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for time periods and optional regions but does not explicitly compare to sibling tools or provide when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It explains the tool's purpose and output but does not disclose limitations, data sources, or how elevation is determined. Additional context (e.g., accuracy, model assumptions) would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the tool's core purpose. Every word adds value, and there is no redundancy or unnecessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain the return format more thoroughly. It mentions 'risk classification and descriptive assessment' but omits details like classification categories or data range. For a tool with 3 parameters, this is marginally adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters are already well-documented. The description adds 'elevation relative to a reference water level' but does not provide additional semantic meaning beyond the schema. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool assesses flood risk at a given location using elevation and water level. It specifies the output (risk classification and assessment), distinguishing it from sibling tools like terrain_elevation which only provide elevation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for flood risk assessment but provides no explicit guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. It correctly implies a read-only data retrieval operation, but does not disclose details such as data limits, pagination, or how commodities are returned (since no commodity parameter exists in the schema). The description is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is direct and free of unnecessary words or redundancy. It efficiently conveys the core function without filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with four parameters and no output schema or annotations, the description provides only a high-level overview of what is returned ('by commodity'). It does not explain the structure of the response, how commodities are identified, or any constraints (e.g., available years). While sufficient for basic understanding, more detail would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes all four parameters (reporter, partner, year, flow) with clear definitions and an enum for flow. The description adds value by stating that the output includes 'import/export values by commodity', which clarifies the granularity of the result beyond what the schema mentions. This is a meaningful supplement even with 100% schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: retrieving bilateral trade data (import/export values by commodity) between two countries. It uses a specific verb ('Get') and resource ('bilateral trade data'), and distinguishes from sibling tools like trade_balance (overall balance) or trade_partners (list of partners).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool over alternative trade tools such as trade_commodity, trade_timeseries, or trade_partners. The description does not mention when not to use it or specify prerequisites, leaving the agent to infer context from the sibling list alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It states 'Get historical weather data' which implies a read-only operation, but lacks details on data range, availability, or restrictions. This is minimal but not contradictory.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no unnecessary words. It is front-loaded with the verb and resource, making it easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, the description does not specify what kind of weather data is returned (e.g., temperature, precipitation). It is adequate for a simple retrieval tool but could be more informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with brief descriptions for lat, lng, and date. The tool description does not add additional meaning beyond the schema, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Get' and clearly identifies the resource as 'historical weather data' with constraints 'for a specific date and location'. This distinguishes it from sibling tools like weather_current and weather_forecast.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for historical data but provides no explicit guidance on when to use this tool versus alternatives. No exclusions or alternative tool names are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist. The description mentions 'low cloud cover periods' but does not disclose algorithm, data source, forecast vs. historical, or what defines 'optimal'. Basic transparency but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence of 15 words, front-loaded with the core purpose. Every word adds value; no redundancy. Highly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no description of return format. The tool likely returns optimal windows, but the description neither specifies data structure nor dimensions. Adequate for simple use but incomplete for precise invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with clear descriptions for lat, lng, and days. The description adds context about 'low cloud cover' but does not significantly enhance parameter understanding beyond the schema. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool 'Find optimal satellite imaging windows' with specific focus on 'low cloud cover periods' and scope 'for a location over the next N days'. It uses a specific verb and resource, and distinguishes from sibling weather tools that provide current conditions or forecasts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs. alternatives like sentinel_search or landsat_metadata. The description implies usage for planning satellite captures but does not provide when-not-to-use or reference siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It lists outputs but doesn't disclose side effects, permissions, rate limits, or if changes are reversible. As a read-only stat tool, it's likely safe, but this is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with a dash, efficient and front-loaded. Every word adds value: verb, resource, scope, and list of outputs. No unnecessary text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple stat tool with 4 numeric params, description sufficiently covers purpose and outputs. Could mention if data is real-time or historical, or any bounding box size limits, but not critical for basic usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% description coverage, so parameters are well-defined. Description adds context by mentioning 'bounding box' but does not go beyond schema in explaining parameter usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states tool provides traffic statistics for a bounding box, listing specific outputs (total aircraft, altitude/speed distribution, top countries). Distinguishes from sibling tools like aircraft_track or aircraft_live which focus on individual flights or live positions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage context is implied (when you need aggregated statistics for an area), but no explicit guidance on when not to use it or alternatives. Sibling tools exist for more specific queries, but description doesn't reference them.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions 'Queries' and 'Returns', implying a read operation, but does not disclose any behavioral traits like authorization needs, rate limits, or potential side effects. This is adequate but not detailed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loaded with the core purpose, and each sentence adds value: first defines the main action, second specifies the country code format and return fields. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the main return fields (brightness, confidence, FRP, timing) but does not specify limits on number of results, pagination, or error behavior. Given the absence of an output schema, these details would be helpful but not critical for a straightforward query tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents all three parameters. The description adds context about return fields (brightness, confidence, FRP, timing) and country code format, but this is supplementary and not essential for understanding parameters themselves.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Query', the resource 'NASA FIRMS active fire detections', and the scope 'within a country'. It also distinguishes from sibling tools like firms_active_area and firms_active_point by specifying country-level queries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the use of ISO country codes but does not explicitly state when to use this tool versus alternatives such as firms_active_area for arbitrary regions. There is no guidance on when not to use it or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries burden. It discloses the two-step filtering process, but lacks details on rate limits, required permissions, or any side effects. Adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences front-loading purpose then method. No redundant or irrelevant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, but description fails to describe return values or format. Sibling tools likely return fire data, but this is not clarified. Incomplete for a search/query tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all 4 parameters with descriptions (100% coverage). Description adds context on bounding box/haversine but does not further clarify parameter semantics. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Find' and resource 'active fires' with specific scope 'near a geographic coordinate within a given radius'. Distinguishes from siblings by specifying point-radius approach rather than area or country.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes internal algorithm (bounding box + haversine filtering), implying accuracy benefits. Does not explicitly state when not to use or contrast with alternatives, but provides sufficient context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions the Haversine formula and returned units, but does not disclose precision, limitations (e.g., antipodal points), or computational cost. Adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that is informative and front-loaded with the purpose. No unnecessary words; every part earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description explains the return format (three distance units). The tool is simple, parameters are fully documented, and the output is covered. Could mention edge cases or precision, but overall sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions (lat/lng with ranges). The description adds context about the formula and return units but does not elaborate on parameter meaning beyond what the schema provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool calculates great-circle distance between two points using the Haversine formula, and lists return units (km, miles, nautical miles). This clearly distinguishes it from sibling tools like geo_bbox or geo_elevation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for distance calculation but does not provide explicit guidance on when to use versus alternatives, nor when not to use. With many sibling geo tools, lack of differentiation is a gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It discloses the basic behavior: returning bridges, tunnels, etc., within a bounding box. However, it omits details about data sources, result limits, or permissions, which is acceptable for a simple query tool but not highly transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, 12 words, front-loaded with the verb 'Find'. Every word is necessary, no fluff. Highly concise and structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple bounding box query tool, the description covers the essentials: what is found and the spatial scope. Schema fully documents parameters. Lack of output schema is compensated by the explicit list of result types. Minor omissions (e.g., data source) do not significantly hinder use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Parameter descriptions in the schema already define east/west/north/south as coordinates. The tool description adds that these define a bounding box, which is useful context but not substantial. With 100% schema coverage, baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies the verb 'Find', the resource type (bridges, tunnels, ferry terminals, train stations), and the scope (bounding box). It clearly distinguishes itself from sibling infrastructure tools like infra_cables or infra_energy by listing specific transport infrastructure types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when transport infrastructure within a bounding box is needed, but no explicit guidance on when to use this tool versus alternatives like geo_bbox or other query tools. No exclusions or alternatives are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the tool counts and classifies buildings, implying read-only behavior. However, it does not detail potential side effects, authorization needs, rate limits, or return value structure. For a read tool, this is adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that conveys the tool's purpose without any fluff. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple bounding box query tool, the description covers the core purpose. It lacks details on return format, but without an output schema, some brevity is acceptable. The description is reasonably complete given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage with each parameter described. The description does not add additional meaning beyond what the schema already provides for the bounding box coordinates, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool counts and classifies buildings in a bounding box, which is a specific verb-resource combination that distinguishes it from sibling OSM tools targeting other features like airports, water, or industrial infrastructure.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for building classification tasks but provides no explicit guidance on when to use versus alternatives or when not to use. While the purpose is clear, it lacks explicit context about when to prefer this tool over other OSM tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description discloses the tool's purpose and outputs but omits behavioral traits such as data freshness, required permissions, or performance considerations. It does not contradict any annotation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that efficiently conveys the tool's core functionality without extraneous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description name-drops key outputs (fishing hours, vessel count, top flag states), which is helpful. However, it lacks details on return format or pagination, but the tool is a straightforward analytical query.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All 6 parameters are fully described in the schema (100% coverage), and the description adds context that the tool analyzes an area over a date range, but does not provide additional meaning beyond what the schema already conveys.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool analyzes fishing activity (specific verb-resource pair) and lists the outputs (fishing hours, vessel count, top flag states). It distinguishes from siblings like ship_track or ship_search, which focus on individual vessels or positions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (for aggregated fishing analysis) but does not explicitly state when not to use or mention alternatives among sibling tools like ship_area or ship_dark. More guidance would help differentiate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only implies a read operation with 'Get'. It does not disclose any behavioral traits such as authentication needs, rate limits, or potential side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, well-structured sentence that immediately conveys the tool's purpose with essential details. No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description adequately covers what the tool returns given its simplicity. No output schema exists, but the listed data points (total satellites, orbital stats, launches) provide sufficient context for usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters and 100% schema coverage, the description adds no parameter information but correctly states the output, which is sufficient for a parameterless tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves Starlink constellation status with specific data points like total satellites, orbital statistics, and launch dates. It uses a specific verb ('Get') and resource ('Starlink constellation status'), distinguishing it from sibling tools like space_satellites or space_tle.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool over siblings. While the specificity implies a niche, there is no mention of alternatives or context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavior. It includes the formula and value range, but does not mention potential division-by-zero issues, required input preprocessing, or the output format beyond range. This is adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences, front-loaded with the formula and key information. No unnecessary words, and the structure is logical.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description states the output range but does not specify the exact return type (e.g., a single number) or behavior for edge cases (e.g., division by zero). Given no output schema, more detail would be beneficial for a complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with good parameter descriptions. The tool description adds value by providing typical band assignments (e.g., Sentinel-2 Band 3, Landsat Band 3) and the formula, which helps understand parameter meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool calculates NDWI from Green and NIR bands, provides the formula, and lists applications. It is specific but does not explicitly differentiate from sibling spectral indices like NDVI or NBR.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear usage context by listing applications (water detection, flood extent, drought monitoring). However, it lacks explicit when-not-to-use or comparisons to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavioral traits. It states detection but gives no details on output, safety, or side effects. With zero annotations, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with front-loaded purpose and specific examples, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks output schema and doesn't hint at return format (e.g., list, summary). For a detection tool, more completeness would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with parameter descriptions. The tool description adds context by explaining the bounding box is for anomaly detection, enhancing meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the function: detect anomalous aircraft behavior in a bounding box, with explicit examples (low altitude, loitering, emergency squawks, no callsign). This distinguishes it from sibling tools like aircraft_flights or aircraft_live.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implied usage for anomaly detection in a region, but no explicit guidance on when not to use or alternatives among many aircraft-related siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It indicates a retrieval operation without side effects, which is appropriate. However, it lacks details on what 'recent' means (though defaults are in the schema) and does not mention ordering or limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, well-structured sentence that conveys the tool's core purpose without unnecessary words. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is adequate but could be more informative about the returned data, ordering, or pagination. It covers the essentials but lacks depth for a complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all parameters; the description adds only the phrase 'by ICAO code' which clarifies the airport parameter. This meets the baseline but adds no significant meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get', the resource 'recent departures', and the method 'by ICAO code'. It effectively distinguishes from siblings like aircraft_arrivals (arrivals) and aircraft_flights (broader flight information).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies using the tool when recent departures from a specific airport are needed. It does not explicitly state when not to use or list alternatives, but the context with sibling tools makes the differentiation clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It discloses output fields but does not mention rate limits, authentication, pagination behavior, or data source. For a read-only tool, this is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence followed by a list of return fields. It is concise and front-loaded, with no extraneous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with two parameters and no output schema, the description provides sufficient context: what it does, the filter, and key return fields. It covers the essentials without gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with both parameters described. The description adds minimal new semantics beyond the schema, simply restating the minimum magnitude filter. Baseline 3 is appropriate as the schema already defines parameters well.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves recent earthquakes with a minimum magnitude filter, and lists the return fields (location, magnitude, depth, tsunami warning, alert level). It is distinct from sibling tools like quake_search or quake_detail by focusing on recent events.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for recent earthquakes but does not explicitly differentiate from alternatives like quake_search or quake_stats. It lacks guidance on when to choose this tool over others, leaving the agent to infer from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description is minimal, stating only the forecast period and included data types. It does not disclose behavioral traits such as data source, update frequency, or limitations. With no annotations provided, the description carries the full burden but offers only basic transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that conveys all essential information without redundancy. Every element serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (2 simple parameters, no nested objects, no output schema), the description adequately covers the tool's purpose, inputs, and outputs. It provides sufficient context for an AI agent to understand and select the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with 'lat' and 'lng' described as Latitude/Longitude. The description adds no extra meaning beyond 'for a coordinate', so it aligns with the baseline score for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves a 7-day weather forecast for a coordinate, specifying daily temperature, precipitation, wind, sunrise, and sunset. This distinguishes it from sibling tools like 'weather_current' and 'weather_historical', which address different timeframes or conditions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for a 7-day forecast at a coordinate but does not explicitly state when not to use or compare with alternatives like 'weather_current' for current conditions. The context from sibling names provides cues, but the description itself lacks direct guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses the simple calculation method and acknowledges potential inaccuracy near timezone borders, providing transparency about the tool's limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. First sentence states purpose, second adds important accuracy caveat. Efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema is provided, and the description does not indicate what the tool returns (e.g., timezone name, offset). This is a significant gap for a tool with no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers param descriptions (lat/lng ranges) at 100%. Description adds value by explaining the calculation formula (offset = round(lng / 15)), giving context beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it estimates timezone at a geographic coordinate based on longitude, with a specific verb 'Estimate' and resource 'timezone'. This distinguishes it from siblings like geo_elevation or geo_reverse.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for quick timezone estimation but does not explicitly state when to use this tool versus alternatives or provide any exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses that EPIC captures 12-22 images per day and returns image URLs, captions, and centroid coordinates. This adds behavioral context beyond the basic purpose, though it omits potential error conditions or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is highly concise: two sentences with no wasted words. The first sentence states the core action, and the second adds valuable context about image count and return fields. Front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (single parameter, no output schema), the description adequately covers what the tool does and what it returns. It does not discuss error handling or edge cases, but for a straightforward date-based retrieval, this is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single 'date' parameter. The tool description reinforces the parameter's role ('specific date') but does not add new semantics beyond what the schema's description already provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Get DSCOVR EPIC full-Earth photographs for a specific date.' It specifies the resource (DSCOVR EPIC photographs) and distinguishes itself from siblings like nasa_epic_latest (likely latest image) and nasa_epic_archive.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for a specific date but provides no explicit guidance on when to use this versus alternatives like nasa_epic_latest or nasa_epic_archive. No exclusions or when-not-to-use scenarios are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions the instrument and L1 point but does not disclose update frequency, data freshness, rate limits, or authentication requirements. Behavior is straightforward but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two focused sentences. It front-loads the key purpose and immediately lists output contents, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (no parameters, no output schema), the description adequately covers what the tool returns. It could mention the image format or coordinate system for completeness, but the provided list is sufficient for an agent to understand the tool's role.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and schema coverage is 100%. The description adds meaningful context by specifying the return values (image URL, caption, coordinates, sun position), which is sufficient for a parameterless tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves the latest full-disk Earth photograph from DSCOVR's EPIC instrument and lists the returned data (image URL, caption, coordinates, sun position). It distinguishes itself from siblings like nasa_epic_archive and nasa_epic_date by specifying 'latest'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for the most recent image but does not explicitly state when to use this tool over alternatives, nor does it provide exclusions or prerequisites. Usage context is inferred from the name and description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the formula, output range (-1 to 1), and typical applications. However, it does not mention prerequisites like atmospheric correction or potential division-by-zero issues, which would be helpful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences that cover purpose, formula, and usage. No redundant or irrelevant information. Front-loaded with the main action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 4 simple numeric parameters and no output schema, the description adequately explains what the tool computes and why. It could mention that the return value is a single number, but overall it is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed descriptions for each parameter (band reflectance values, typical sensors). The description adds the formula and application context but does not further clarify parameter usage beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool calculates Bare Soil Index from four band reflectances, provides the formula, and lists its applications (mapping exposed soil, desertification monitoring, distinguishing bare soil). It is specific and distinguishes from sibling spectral indices.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for soil-related analysis but does not explicitly state when to use BSI over other indices like NDBI or NDVI. No exclusions or alternatives are mentioned, leaving the agent to infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that it returns current data and lists pollutants. However, it lacks details on update frequency, data source, or limitations (e.g., API key requirements, availability per location).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with the main action and resource, no unnecessary words. Efficient and scannable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with two parameters and no output schema, the description sufficiently explains the tool's function and includes relevant pollutant names. It is complete for this low complexity level.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions for lat and lng. The description adds no new parameter-specific meaning beyond the schema; it only confirms the coordinate is used for location. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'current air quality index and pollutant concentrations', listing specific pollutants (PM2.5, PM10, NO2, SO2, CO, Ozone). It distinguishes from siblings like atmosphere_uv and env_air_pollution by focusing on current air quality at a coordinate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for current air quality at a single point but provides no explicit guidance on when to use this tool versus alternatives like env_air_pollution or other environmental tools. No exclusions or conditions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must convey behavioral traits. It correctly indicates a read-only reference table, but does not disclose update frequency, data source, or whether results are static. Additional context would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, well-structured sentence conveys all necessary information without redundancy. Every word is meaningful and earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter reference table, the description is complete. It explains what the tool returns (band info) and is sufficient given the Landsat context. No output schema exists, but the description covers the return content adequately.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and schema description coverage is 100%. The description adds meaning by specifying the content (wavelengths and resolutions), which goes beyond the empty schema. Baseline for zero parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is a reference table for Landsat 8/9 OLI/TIRS spectral bands, specifying the included attributes (wavelengths and resolutions). It uses a specific verb-resource pair and distinguishes from sibling tools like landsat_search or spectral_ndvi.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when band wavelengths or resolutions are needed, but does not explicitly state when to use this tool versus alternatives (e.g., spectral index tools that might need this data). No exclusionary guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool returns a list of dates, which is transparent about the output, but does not disclose any behavioral aspects such as rate limits, authorization needs, or side effects. For a simple read-only tool, this is adequate but not exemplary.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at two sentences. The first sentence clearly states the action and resource, and the second adds context about the archive. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that the tool has no parameters and no output schema, the description is complete. It explains what the tool does (list dates) and what it returns (a list of dates). No additional context is necessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so schema coverage is 100%. The description adds value by explaining the purpose and output, which is sufficient for a parameterless tool. Baseline for zero parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all available dates in the DSCOVR EPIC image archive. The verb 'list' and resource 'dates' are specific, and the tool is distinct from siblings like 'nasa_epic_date' and 'nasa_epic_latest' which likely retrieve images for a specific date or the latest image.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives. It implies usage for discovering available dates, but lacks guidance on prerequisites or when to choose another tool like 'nasa_epic_date'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It describes a stateless conversion with no side effects, but does not mention any limitations, auth requirements, or rate limits. Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the purpose, and contains no extraneous information. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple conversion tool with 100% parameter coverage and no output schema, the description adequately covers what the tool does and the two modes of operation. It could mention the expected output format briefly, but it's largely complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. The description adds value by clarifying the mutual exclusivity of input groups (lat+lng vs mgrs), which is not enforced by the schema. It also reiterates the precision range.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool converts between MGRS and lat/lng coordinates, with bidirectional conversion explicitly mentioned. It is distinct from sibling geo tools like geo_bbox or geo_distance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool: when you have an MGRS string or lat/lng coordinates. It implies mutual exclusivity of inputs. However, it does not explicitly exclude alternatives or provide guidance on when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description clearly indicates a read-only static reference table with no side effects. It straightforwardly describes the output content, leaving no hidden behaviors. A score of 4 reflects adequate transparency for a simple query tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, precise sentence that conveys all essential information without wordiness. Every word serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given it is a simple reference tool with no output schema, the description covers what is returned (wavelengths and resolutions) and the scope (all 13 bands). It could potentially mention the format or typical use, but it is sufficiently complete for the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the schema description coverage is 100% (empty). Thus, the description does not need to elaborate on parameters. Baseline for 0 params is 4, which is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states it is a reference table for all 13 Sentinel-2 MSI spectral bands with wavelengths and resolutions. This clearly distinguishes it from sibling tools like landsat_bands (different satellite) and other sentinel tools (which deal with imagery).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives, such as sentinel_search for imagery. The context implies it is for static band lookups, but no when-not-to-use or alternative tool mentions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description discloses the calculation formula and its advantages (atmospheric/soil correction). Does not mention authorization, rate limits, or destructive behavior; however, for a simple calculation tool, the description is sufficiently transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences with zero wasted words. Front-loads the core purpose and formula, then provides context. Excellent structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple calculation tool with three numeric inputs and no output schema, the description explains the formula, its purpose, and when to use it. No additional information is necessary for correct use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all three parameters with descriptions and ranges. The description repeats the formula but adds no parameter-specific details beyond the schema. Baseline 3 is appropriate given full schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool calculates EVI from NIR, Red, and Blue bands, provides the formula, and differentiates from NDVI by explaining its advantage in high-biomass regions. This strongly distinguishes it from sibling tools like spectral_ndvi.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when EVI is useful (high-biomass regions where NDVI saturates), implying when not to use it. Implicitly suggests alternatives like NDVI, though not named directly. Sibling tool list includes spectral_ndvi for context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description delivers formula, data range, and typical uses. For a non-destructive calculation, this covers behavioral expectations adequately. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences: first states purpose and definition, second provides formula and range, third lists applications. No unnecessary words; information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, formula, and applications. Lacks explicit statement of output format (single numeric value) but that is implied. Good enough for a simple calculation tool without output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds formula and use context but no new param-specific details beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool calculates NBR from NIR and SWIR reflectance, provides the formula and range, and describes applications (wildfire burn severity, post-fire recovery, dNBR). Distinguishes well from sibling spectral indices.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes when to use (burn severity, post-fire recovery) but does not explicitly contrast with other indices or provide when-not-to-use guidance. Context is clear enough for typical use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It describes the calculation, output range (-1 to 1), and interpretation (higher values = denser built-up), which is sufficient for a pure computation tool. No side effects or destructive actions are expected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (4 sentences) and front-loaded with the core purpose. Every sentence adds value: formula, range, use case, and interpretation. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 parameters, no output schema), the description is complete. It explains the index, values, and application. Sibling tools are similar but this description sufficiently distinguishes NDBI from other spectral indices.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with clear parameter descriptions (e.g., typical band assignments). The tool description adds the formula context but does not significantly enhance understanding beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool calculates NDBI from SWIR and NIR band reflectance values, provides the formula, and specifies its use for mapping urban areas. This distinguishes it from sibling spectral indices like NDVI (vegetation) or NDWI (water).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates the tool is used for mapping urban areas and built-up land, providing clear context for when to use it. However, it lacks explicit exclusion criteria or comparison with alternatives like spectral_ndvi (vegetation) or spectral_bsi (bare soil), though the sibling list implies differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description fully discloses the tool's behavior: it computes a bounding box from center point and radius. It is a pure computation with no side effects, so additional disclosure beyond what is stated is minimal. However, could specify the geometric model (e.g., spherical approximation) for completeness.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences: first defines the operation and output, second suggests use cases. No redundancy or unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple computational tool with no output schema, the description fully communicates the purpose, inputs, and outputs. It is self-contained and sufficient for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all parameters with descriptions (100% coverage). Description adds value by explicitly defining the output format (south, west, north, east), which is not in the schema. This clarifies how the radius maps to the bounding box edges.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'Compute' and the resource 'bounding box', with explicit output components (south, west, north, east). Distinguishes from sibling tools like geo_distance and geo_elevation which serve different spatial purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides a usage context ('spatial queries and map viewports') but does not explicitly state when not to use this tool or mention alternative sibling tools. Implicit guidance exists but is not comprehensive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses it returns a count and sorted list of dates, which is transparent about the output and non-destructive nature.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two efficient sentences without waste; first states purpose, second provides usage context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Completely covers the tool's function for a simple list tool with 2 params and no output schema; tells what it returns.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for lat and lng, so description adds minimal new meaning beyond contextualizing 'geographic coordinate'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists Landsat 8 imagery dates for a coordinate, distinguishing it from sibling tools like landsat_search or nasa_earth_image.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains it is useful before requesting imagery, providing clear context but lacking explicit when-not-to-use or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry the burden. It explains the formula and output range (-1 to 1), but does not disclose any edge cases, validation behavior, or side effects. The schema already enforces input ranges, so the description is minimally adequate but lacks deeper behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with three short sentences covering the action, formula, range, and use case. It is front-loaded with the verb 'Calculate' and contains no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter tool with no output schema or nested objects, the description provides all essential information: what it does, how it works (formula), output range, and typical application. No significant gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the description adds value by referencing typical satellite band sources (Sentinel-2 Band 8, Landsat Band 5), which helps users select appropriate inputs. However, it does not add meaning beyond the schema's own descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: calculate NDVI from NIR and Red bands. It provides the formula and explains the index's use for vegetation health assessment, distinguishing it from sibling tools like spectral_evi or spectral_ndwi.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes context for when to use the tool ('assessing vegetation health, density, and agricultural monitoring'), but does not explicitly mention when not to use it or provide comparisons with similar indices. The guidance is clear enough for a straightforward calculation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the computation of NDBI and interpretation of difference. It is a safe, read-only calculation; no side effects are mentioned but none expected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no fluff. Everything is essential and front-loaded. The description is perfectly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 4 parameters, no output schema, and no annotations, the description explains what is computed and why. It could mention the expected output (e.g., a difference value or map), but is otherwise complete for a computational tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with parameter descriptions. Description adds value by explaining how the parameters (SWIR and NIR reflectances for two dates) are used to compute NDBI, which goes beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description states specific verb+resource: 'Urban expansion detection using NDBI'. It clearly names the index and bands (SWIR, NIR) and distinguishes from sibling tools like change_vegetation or change_water.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly indicates when to use: for urban expansion detection via NDBI. It does not explicitly state when not to use or list alternatives, but the context is clear among the many spectral change tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, but the description states it returns a summary, implying a read-only operation. It does not hide any important behavioral traits; however, it does not explicitly state that it has no side effects. Still, it is adequate for a listing tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: the first explains what it lists, the second specifies the output scope. No wasted words, front-loaded with action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no parameters, the description fully explains what the tool returns (list of sources, API key status, tool counts, and summary). It is complete for its purpose.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, so baseline is 4. The description adds no parameter details because none are needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it lists all satellite-mcp data sources, their API key status, and tool counts, with specific numbers (27 categories, 161 tools). This immediately differentiates it from sibling tools which are specific data queries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives, but its role as an overview/discovery tool is implied by contrast with the sibling tools (e.g., agri_crop_health, etc.). It lacks explicit 'when not to use' guidance but is clear enough for an agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: security (no eval, recursive-descent parser), supported operations (arithmetic, parentheses, numeric literals, band variables), and limitations (no function calls or arbitrary code).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured paragraph that front-loads the purpose, provides a clear example, and explains security. Every sentence adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers purpose, security, syntax, and example. However, it lacks mention of error handling (e.g., invalid expression or missing bands) and the return value, which are minor omissions for a custom math tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters. The description adds a concrete example and explains the parser's safety, going beyond the schema by clarifying the expression syntax and security model.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Evaluate a custom band math expression using a safe expression parser.' It specifies the verb (evaluate), the resource (custom band math expression), and distinguishes from sibling spectral index tools like spectral_ndvi by emphasizing custom expressions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides an example and explains supported operations, but does not explicitly state when to use this tool versus the specific spectral index tools (e.g., spectral_ndvi). It implies usage for custom indices not covered by siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the formula, L parameter behavior (default, range, effects of different values), and mathematical relationship to NDVI. Fully transparent for a calculation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single paragraph front-loaded with purpose, immediately followed by formula, parameter details, and usage context. Every sentence adds information; no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, description thoroughly covers inputs, formula, parameter semantics, and use cases. Adequate for a simple mathematical index calculation tool with moderate complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (baseline 3). Description adds value by explaining the formula, L parameter's soil correction role, and typical values for different vegetation densities. Exceeds baseline by providing context not in schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool calculates SAVI from NIR and Red bands, including the formula. It distinguishes itself from siblings like NDVI by emphasizing soil adjustment for arid/semi-arid regions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: 'Used in arid/semi-arid regions where soil background significantly affects NDVI.' Missing explicit when-not or alternatives, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![satellite-mcp MCP server](https://glama.ai/mcp/servers/badchars/satellite-mcp/badges/card.svg)](https://glama.ai/mcp/servers/badchars/satellite-mcp)

Score Badge

Copy to your README.md:

[![satellite-mcp MCP server](https://glama.ai/mcp/servers/badchars/satellite-mcp/badges/score.svg)](https://glama.ai/mcp/servers/badchars/satellite-mcp)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/badchars/satellite-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server