Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that results are 'relevance-ranked' and searches across multiple fields, which is useful. However, it does not mention other behavioral traits such as case sensitivity, pagination, or behavior with no results. It is moderately transparent but 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise at two sentences, with no wasted words. The first sentence states the core functionality, and the second provides concrete usage examples. It is well-structured and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 2 parameters, no output schema, and no annotations, the description is adequate for basic understanding but lacks details on return format, parameter constraints, and edge cases. It covers the purpose and usage examples but is not fully complete for complex queries.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50% (only query has a description). The description itself does not elaborate on parameters like 'limit' or provide additional meaning beyond the schema. It adds no parameter-specific information, so it fails to compensate for the schema's lack of coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Relevance-ranked free-text search across every record's title, location and description.' It specifies the verb (search), resource (records), and scope (title, location, description), and differentiates from sibling tools like 'search_sightings' by providing example use cases ('thematic digs') and specific query terms.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly provides example use cases ('for thematic digs') and query terms ('FLIR', 'orb', 'triangular'), which helps the agent understand when to use it. However, it does not explicitly state when not to use this tool or mention alternatives among the sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It mentions what is included (full description, source link) but does not disclose side effects, error handling, or permissions. 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence of 18 words, front-loading the core action and providing an example. Every word adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple get-by-ID tool with one parameter and no output schema, the description covers the key inclusions (full description, source link). The sibling list provides context. Minor omission: does not explain return format or error states.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes the 'id' parameter as 'record id, e.g. 'pursue-042''. The description adds the same example without providing new semantic meaning beyond the schema. 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.

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 'full record for one UAP file', and specifies the identifier format with an example. It distinguishes itself from siblings like full_text_search by being a direct retrieval by ID.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when you have a specific ID and need the full record, but it does not provide explicit guidance on when to avoid this tool or suggest alternatives. Sibling tools are listed separately but not contrasted.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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 ranking function but does not disclose output format, pagination, authentication needs, or any side effects. Minimal behavioral 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single 15-word sentence, concise but lacking structure. It is front-loaded with the purpose, but every word could be expanded to include more useful detail without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

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 incomplete. It does not explain what the ranking output contains, how results are sorted, or how 'declassified records' are counted. The tool is simple but needs more context for correct use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain the 'limit' parameter. The schema provides defaults and bounds, but the description adds no additional meaning or usage context for the parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool ranks incident locations by the number of declassified records mentioning them, using verb 'rank' and specific metric. It distinguishes from siblings like search functions and stats by focusing on location ranking based on mention frequency.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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. Usage is implied but not compared to alternatives such as search_sightings or stats. The description assumes the agent will infer context from sibling names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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-only operation but does not explicitly state side effects, permissions, or return behavior. More detail 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys the tool's purpose and content without extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

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 hints at the return value (cases with records and importance). For a tool returning predefined cases, this is mostly complete, though specifying the structure would help.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameter is already well-defined with an enum. The description adds context by listing the values in parentheses, but does not significantly enhance understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it returns curated, historically significant cases with matching records and why they matter. It lists specific cases, making the purpose distinct from siblings like full_text_search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies using this for predefined notable cases, but does not explicitly guide when to use it versus alternatives (e.g., full_text_search for broad search). No mention of 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.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description carries full burden. It reveals key behaviors: distance-sorted results and exclusion of off-world records. However, it doesn't explicitly state that the operation is read-only or describe any 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, front-loaded with key info. Could be slightly more structured (e.g., listing parameters) but no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter tool with no output schema and no annotations, the description covers purpose and key behaviors but lacks details on pagination, return format, or how results are presented. Adequate but could do more.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so description must compensate. It adds context for latitude, longitude, and radius_km (radius in km) but does not explain limit or the meaning of radius_km's constraints (default, min, max). No details on required vs optional.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool finds declassified UAP incidents near a lat/lon, sorted by distance, and excludes off-world records. This distinguishes it from siblings like hotspots or notable_cases.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates when to use (spatial search for incidents) but does not explicitly mention when to prefer alternatives like search_sightings or full_text_search.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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 states 'Returns matching records (brief form)', omitting details about whether the operation is read-only, destructive, any authentication needs, rate limits, or pagination. The phrase 'brief form' is vague.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys the core purpose and search dimensions. Every word serves a purpose; no fluff or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 7 parameters, no output schema, and no annotations, the description is insufficient. It omits critical details like the 'limit' parameter behavior, result format details, and handling of empty results. An agent would lack enough context to use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description covers 5 of 7 parameters (query, agency, type, location, year range) but omits 'limit' and does not explicitly name 'year_start' and 'year_end' (though implied by 'year range'). The schema already provides descriptions for most parameters, so the description adds marginal value. A 3 is appropriate given schema coverage >50%.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as a search over 'declassified PURSUE UAP records' with specific searchable dimensions (free text, agency, file type, year range, location). The verb 'Search' and resource are clear, but it does not differentiate from the sibling 'full_text_search', which may have overlapping functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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 'full_text_search', 'get_sighting', or 'stats'. There are no examples or context for appropriate use cases, making it harder for an agent to choose correctly among similar siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description carries the full burden. It states the tool provides summary statistics but does not disclose behavioral traits such as data freshness, caching, or whether it aggregates live data. Minimal transparency beyond 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with no extraneous information. Conciseness is good, but the term 'breakdowns' is vague and could be more specific about what is included.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and no output schema, the description is adequate but minimal. It lacks details about the output format (e.g., JSON structure) or scope (e.g., time range). For a simple stats tool, more context would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, and schema coverage is 100% (empty properties). The description adds no parameter info because none exist. Baseline of 4 is appropriate for a parameterless tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it provides summary statistics for the PURSUE release with breakdowns by agency, file type, and era. However, it does not differentiate from siblings like timeline or hotspots, which might also offer aggregated data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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 it is for overall statistics, but lacks context about when other tools are more appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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 discloses the aggregation behavior (counting records per time period), but lacks details on side effects, authentication, or data source. For a read-only aggregation, this is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, well-structured sentence that front-loads the action (Count) and resource, with no superfluous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one optional parameter and no output schema, the description is largely complete. It could mention the output format (e.g., counts per period) but the current level is acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description explains the granularity parameter's purpose (per decade or per year), adding meaning beyond the schema enum. However, it does not mention the default value or the specific time range covered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool counts declassified UAP records by decade or year, with a specific time range (1944–2026). However, it does not differentiate from sibling tools like 'timeline_data', though the verb 'count' and aggregation focus help.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied (to see clustering over time), but there are no explicit when-to-use or when-not-to-use guidelines, nor mention of alternatives among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must disclose behavioral traits. Only states what is returned; no mention of read-only nature, permissions, side effects, 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence front-loads key purpose and output format (coordinates, timeline range). No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a simple tool with one parameter, but lacks return format details, coordinate type, and any limits. Could specify output structure or examples.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage. Description adds no extra meaning to the 'granularity' parameter beyond the enum values; default and choice implications are not explained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it returns per-period records with coordinates for animated timelines/maps, and distinguishes from sibling 'timeline' which likely lacks coordinate data. Verb 'get' is implied.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied for building animated timelines/maps but no explicit when to use vs alternatives or when not to use. Sibling list provides context but no direct guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.