Data Gov Sg

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

No annotations exist, and the description only states it provides 'current' readings without explaining update frequency, data source, or coverage scope. Significant 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.

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

A single, front-loaded sentence conveys essential information with no wasted words. It is appropriately concise.

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 no-parameter tool returning simple readings, the description is adequate but could mention update frequency or data confidence. Without output schema, more detail on return 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?

With zero parameters, the baseline is 4. The description adds value by clarifying the measurement (PM2.5 in µg/m³) and regional grouping, which is not evident from the empty 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 'Current PM2.5 µg/m³ readings by region,' specifying the pollutant, unit, and geographic grouping, which distinguishes it from siblings like air_quality_psi or uv_index.

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 siblings like air_quality_psi or weather_now. The description lacks any context about alternatives or exclusions.

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 carries full burden but only states 'Current PSI', omitting details like update frequency, data source, or whether the value is real-time or cached. Such minimal disclosure leaves behavioral aspects unclear.

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 that front-loads the key purpose and lists regions. Every word is essential, 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 tool with no parameters and no output schema, the description is minimally adequate. It conveys the basic function but lacks details on return format, data freshness, or geographic scope, leaving some ambiguity about expected output.

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 tool has zero parameters, so the baseline score is 4. The description adds no parameter meaning beyond the empty schema, but that is acceptable given no parameters exist.

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 returns the current Pollutant Standards Index (PSI) by region, listing the five regions explicitly. It distinguishes itself from the sibling tool 'air_quality_pm25' by focusing on a different index.

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 'air_quality_pm25' or other weather-related tools. The description does not specify prerequisites or context.

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?

Annotations already declare readOnlyHint and idempotentHint. The description adds value by detailing the return format (per-model {score, confidence, signals, raw_response} + combined view) and the API key cost implication, enhancing 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 two sentences with no wasted words. The first sentence conveys the core purpose, and the second adds key details about models and return format.

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?

The description covers the main functionality, default behavior, optional Anthropic integration, and return structure. It omits error handling and scoring methodology, but given the tool's complexity and lack of output schema, it is sufficiently complete.

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 100%, but the description adds clarity by explaining default model, model names, and the optional _apiKey purpose. This goes beyond the schema descriptions.

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 uses specific verbs 'probe' and 'score', and clearly identifies the resource as 'one or more LLMs'. It distinguishes from siblings like 'scan_competitor_ai_presence' by focusing on generic brand/product visibility scoring.

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 explains the default model and optional Anthropic probing, implying usage for AI marketing audits. It does not explicitly state when not to use or mention alternatives, but the context is clear.

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 disclose behavior. It covers routing, argument filling, and result return. It lacks details on error handling or ambiguity, but is adequate for a natural language interface.

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?

Well-structured with a clear opening sentence, usage guidance, and examples. Slightly verbose but effective.

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's complexity (300+ sources, single param, no output schema), the description sufficiently covers purpose, usage, and scope, leaving no critical gaps.

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 100% and the single parameter 'question' is self-explanatory. The description adds examples but no additional semantic depth 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 answers natural-language questions by auto-picking the right data source, and distinguishes itself from sibling tools by not requiring the user to figure out which Pipeworx tool to call. Examples reinforce the purpose.

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?

Explicitly says 'Use when...' and provides a list of query types, making it obvious when to invoke this tool versus alternative tools like query_dataset or search_datasets.

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?

Description adds rich behavioral context beyond annotations: it resolves market, classifies bet, fans out to packs, and returns a comparison. No contradiction with readOnlyHint=true.

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?

Multiple sentences but each adds value. Front-loaded with purpose and input options. Could be slightly trimmed, but remains clear and informative.

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?

Covers input, process, output (evidence packet + comparison), and use cases. No output schema, but description sufficiently explains return. Complete for a complex tool.

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 100%, but description adds concrete details: depth enum meanings (quick=2-3 sources, thorough=full fan-out, default thorough) and market accepts slug, URL, or question text. Adds significant meaning beyond 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 researches a Polymarket bet, inputs (slug, URL, question), and outputs (evidence packet plus comparison). It is specific and distinct from siblings, which are unrelated tools.

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?

Explicitly lists use cases ('should I bet on X?', 'what does the data say?') and implies superiority over manual pack discovery. Lacks explicit when-not-to-use, but guidance is clear.

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 discloses data sources (SEC EDGAR, FAERS, FDA), return nature (paired data + citation URIs), and entity-specific fields. However, it omits safety/error handling (e.g., invalid ticker behavior) and 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?

The description is concise (10 lines) and front-loads purpose and usage triggers. The second half details each type. Some repetition or additional structure could improve clarity, but overall efficient.

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 two parameters, no output schema, and moderate complexity, the description covers entity types, data sources, and use cases. It does not detail return format structure, but for a retrieval tool this 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?

Schema covers 100% of parameters, baseline 3. The description adds context: explains what each type pulls ('revenue, net income...' for company, 'adverse-event report counts...' for drug) and provides examples for values, enhancing meaning beyond schema enums and descriptions.

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 compares 2–5 companies or drugs side by side, with explicit examples of query patterns. It distinguishes from siblings by specifying the comparison and batch capability, which no other sibling tool offers.

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 provides explicit when-to-use triggers like 'compare X and Y', 'X vs Y', and notes it replaces 8–15 sequential calls. It lacks explicit when-not-to-use or alternatives, but the guidance is clear and actionable.

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 carries full burden. The description indicates it's a read operation returning top-N tools. It does not disclose ordering or fallback behavior, but for a simple discovery tool, it is adequate.

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 well-structured, starting with purpose, then usage, then examples. It is slightly verbose but every sentence adds value. Could be trimmed slightly but effective.

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 adequately covers purpose, usage, and param semantics. It tells the agent what to expect (top-N tools with names+descriptions), making it sufficiently complete for a simple discovery tool.

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 100%, so baseline is 3. The description provides example queries but does not add significant meaning beyond the schema definitions for 'query' and 'limit'.

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's purpose: 'Find tools by describing the data or task.' It specifies the verb (find/discover), resource (tools), and output (names+descriptions). It distinguishes itself from siblings by being the discovery tool to call first.

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?

Explicitly tells when to use: 'Call this FIRST when you have many tools available and want to see the option set.' It also lists numerous domains, implying suitability for exploring tools across those areas.

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 the description carries full burden. It discloses return contents (SEC filings, fundamentals, patents, news, LEI, citation URIs) and limitations (company type only). It does not explicitly state read-only, but 'get' implies it. A 4 is appropriate given no contradictions and adequate disclosure.

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 appropriately sized for a complex tool, with front-loaded purpose. Every sentence adds unique information: use cases, data sources, return items, parameter specifics, and citation format. 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?

Given the tool's complexity (aggregates multiple sources) and no output schema, the description is remarkably complete. It covers purpose, when to use, parameter details, return contents, and even citation format. An agent can invoke this tool confidently.

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%, baseline 3. The description adds value by explaining 'type' is only 'company' and that 'value' can be ticker or zero-padded CIK, plus clarifying that names are not supported. This extra context justifies a 4.

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 opens with a clear verb+resource statement: 'Get everything about a company in one call.' It specifies data sources (SEC EDGAR, SEC XBRL, USPTO, news, GLEIF) and uses (tell me about X, profile, research, brief). This distinguishes it from siblings that focus on individual data sources.

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?

Explicitly states when to use: when a user asks for a company profile or when otherwise needing 10+ pack tools. Also provides explicit exclusions: names not supported, and advises to use resolve_entity first. This is a model of usage guidance.

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 states deletion but does not disclose whether the action is irreversible, what happens if the key is missing, or any other side effects. This is insufficient for a mutation tool.

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?

Three sentences, front-loaded with purpose, followed by usage guidance and sibling pairing. No wasted words; every sentence adds value.

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 parameter and no output schema, the description covers purpose, usage context, and related tools. It lacks details on behavior (e.g., irreversibility) but is mostly 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.

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

Schema description coverage is 100%, so the parameter 'key' is already described in the schema as 'Memory key to delete'. The description adds no new information beyond referencing the key, meeting the baseline but not exceeding it.

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 'Delete' and the resource 'a previously stored memory by key'. It distinguishes itself from siblings 'remember' and 'recall', which are for creating and retrieving memories.

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?

Provides explicit when-to-use scenarios: 'when context is stale, the task is done, or you want to clear sensitive data'. It also mentions pairing with related tools. However, it does not explicitly state when not to use, such as when the key does not exist.

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?

Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) are reinforced by the description, which details the process: fetches page, extracts title/description/key links, and emits standard markdown. No contradictions and adds context about output format.

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?

Three compact sentences: one for core purpose, one for process, one for use cases. Every sentence contributes uniquely. No redundancy, appropriate length for the task.

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 two parameters, no output schema, and rich annotations, the description covers purpose, process, output format, and practical use cases. An agent has all needed context to select and invoke this tool correctly.

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 100%, so baseline is 3. The description goes beyond by noting the output is a text blob ready for site-root/llms.txt, providing meaning about the return value that the schema lacks (no output schema). This adds value beyond the parameter descriptions.

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 generates a production-ready llms.txt file for any URL, specifying the verb (generate) and resource (llms.txt). It distinguishes itself from siblings by focusing on this specific output format, while siblings like ai_visibility_check cover different aspects of AI visibility.

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 lists three use cases (getting a client's site indexed, drafting for own project, auditing competitor). It provides clear when-to-use guidance but does not mention when not to use or alternative tools, though no obvious alternative exists 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 are provided, so the description bears the burden. It discloses that the tool returns metadata and column schema, implying a read-only operation consistent with the 'get' prefix. However, it does not elaborate on idempotency, caching, or authorization requirements, leaving behavioral aspects implicit.

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 extremely concise at four words, front-loading the key concept. While efficient, it omits potentially useful context such as return format or usage hints. Every word is relevant, but the brevity sacrifices completeness.

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's simplicity (one parameter, no output schema), the description provides the essential purpose but falls short on completeness. It does not describe the return format (e.g., JSON structure), error conditions, or example output. For a metadata tool, this is minimally adequate but not comprehensive.

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 100%, and the parameter 'dataset_id' is already well-described with an example. The description adds no additional semantic meaning beyond the schema, achieving the baseline. No param-specific elaboration is provided.

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 'Dataset metadata + column schema' clearly states the resource (dataset) and what the tool returns (metadata and column schema). It implicitly distinguishes from siblings like 'query_dataset' (which retrieves data) and 'search_datasets' (which finds datasets), as it focuses on structure rather than content or discovery.

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 such as 'query_dataset' or 'search_datasets'. The description does not specify prerequisites, such as needing a valid dataset ID, or context like using this before querying. No usage rules 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.

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

Discloses rate limit (5 per identifier per day), free usage, and that it doesn't count against tool-call quota. No annotations to contradict.

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?

Concise (~100 words) and well-structured: starts with action verb, covers purpose, usage, exclusions, and limitations. Every sentence adds value.

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?

Despite no output schema, the description fully covers purpose, usage scenarios, parameter guidance, and behavioral constraints. The optional context parameter is sufficiently explained in the schema.

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 100%, and description adds guidance on how to phrase the message (focus on Pipeworx tools/packs, not user prompts). Enhances understanding beyond 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 the tool's purpose: to report bugs, feature requests, data gaps, or praise. It distinguishes itself from sibling tools (data query tools) by being a feedback channel.

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?

Explicitly tells when to use each feedback type (bug, feature/data_gap, praise) and what to avoid (pasting user prompts). Includes rate limit and quota info.

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?

Annotations already mark it as read-only, idempotent, non-destructive. Description adds details about data source (CF analytics-engine), no PII, and caching behavior (5min-1h). Adds value beyond annotations.

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?

Description is a single paragraph with logical flow: result first, then use cases, then technical notes. Efficient and informative without excess.

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 one optional parameter and no output schema, description fully covers purpose, usage context, and behavioral traits. Sufficient for agent to select and invoke correctly.

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?

Single parameter 'window' has clear schema with enum and description. Description adds context: 'Shorter windows surface what's hot right now; longer windows show steady-state demand.' Enhances understanding beyond the enum labels.

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 top tools, packs, and call volume over specified windows. Lists three explicit use cases. Distinct from siblings like discover_tools or search_datasets.

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?

Provides three specific use cases for when to use the tool (hot data sources, canonical choice confirmation, alignment checking). Does not explicitly state when not to use, but positive guidance is strong.

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?

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is clear. The description adds significant behavioral context: it explains the internal logic (walking markets, grouping, checking monotonicity) and what the output contains (ranked opportunities with reasoning). This goes beyond the annotations without contradicting them.

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 efficiently structured: it starts with a clear purpose, then breaks into two labeled modes with concise explanations and an example. Every sentence earns its place, and the information is front-loaded. No unnecessary words or repetition.

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 lack of an output schema, the description adequately describes the output as ranked opportunities with direction and reasoning. It covers both modes and their distinctions. No critical gaps are apparent, though a note about data freshness or rate limits could enhance completeness, but it's not required.

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 100%, so the schema already documents both parameters. The description adds value by providing context: it explains that `event` triggers single-event mode with a slug/URL, and `topic` triggers cross-event mode with a search phrase. Examples further clarify usage, going beyond the schema's basic descriptions.

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's purpose: finding arbitrage opportunities via monotonicity violations on Polymarket. It explains two distinct modes (event and topic), distinguishing how each works, and implicitly differentiates from sibling tools like polymarket_edges by specifying its unique cross-event capability.

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 provides explicit guidance on when to use each mode: single-event mode for checking ordering within a single event, and topic mode for cross-event comparisons. It even gives an illustrative example to clarify when cross-event mode is necessary (e.g., separate events for different deadlines), leaving no ambiguity about usage context.

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?

Annotations indicate readOnlyHint=true, openWorldHint=true, and destructiveHint=false, which the description confirms by stating it reads market data and computes model probabilities. It adds details on data sources (FRED, coinpaprika), the process (grouping by asset, fetching price history once), and output ranking by edge magnitude, going beyond annotations.

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 four sentences long and well-structured: first sentence explains purpose, second details the model, third describes output, fourth gives use case. It's informative without being verbose, though it could be slightly more concise.

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, the description sufficiently describes return value (top N ranked by edge magnitude with suggested trade direction). It covers the high-level process and data sources, but lacks details on return field names or rate limits. However, for a discovery tool, this is adequate.

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?

All three parameters (limit, window, min_edge_pp) are fully described in the input schema with descriptions. The main description reiterates defaults but adds no new semantic meaning beyond what the schema provides. Baseline is 3 due to 100% schema 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 the tool scans high-volume Polymarket markets, finds edges where model probability disagrees with market price, and returns top-ranked opportunities. It specifies the model (lognormal from FRED + coinpaprika) and the use case, distinguishing it from siblings like polymarket_arbitrage.

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?

Explicitly states the tool is for the 'what should I bet on today' question, removing the need to page through markets. While it doesn't explicitly list when not to use, the sibling name 'polymarket_arbitrage' implies an alternative for arbitrage, so guidance is clear but not exhaustive.

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?

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds that it returns leg-by-leg prices and spreads, and mentions the typical price delta. This adds useful behavioral context beyond annotations.

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 paragraph but well-structured with clear sections. It front-loads the main purpose and then details modes and output. Each sentence adds value, though it could be slightly more concise without losing 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 rich annotations and full schema coverage, the description provides complete guidance: purpose, two usage modes, parameter interaction, and output description (prices and spread). No output schema exists, but the return is sufficiently described.

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 100% with descriptions. The description significantly enhances understanding by explaining the two modes ('topic' as shortcuts, explicit tickers overrides), and clarifies how the parameters interact. This exceeds what the schema provides.

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 is a cross-venue spread tool between Kalshi and Polymarket, with a specific verb ('cross-venue spread') and resource ('the same resolving question'). It distinguishes two modes (topic and explicit), making it unique among sibling tools.

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 explains when to use it (for arbitrage signals due to price differences up to 25pp) and describes two modes. It does not explicitly state when not to use, but the context of sibling tools (e.g., polymarket_arbitrage, polymarket_edges) suggests alternatives. The guidance is clear for intended use.

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 empty annotations, the description must disclose behavioral traits. It states a fetch operation and supported parameters but omits details on pagination, read-only nature, error handling, or performance implications.

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 two sentences, front-loaded with main purpose, and contains no redundant words. Every sentence is useful.

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?

The description covers essential purpose and parameters but lacks context on output format, pagination behavior, or error handling. For a data retrieval tool with nested objects, more detail 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?

Schema description coverage is 100%, so baseline is 3. The description adds minimal value by clarifying 'filters' as 'column → value', but for other parameters (limit, offset) it repeats schema info.

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 action ('fetch rows') and resource ('dataset'), listing supported parameters (limit, offset, filter map). It implies a read operation but does not explicitly differentiate from siblings like 'get_dataset' or 'search_datasets'.

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 provides no guidance on when to use this tool versus alternatives, no prerequisites, and no examples. It only lists what the tool supports.

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 carries full burden. It describes retrieval, listing, and scoping behavior. Lacks details on what happens if key doesn't exist (null vs error), but overall 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?

Three sentences with no redundancy. Front-loaded with purpose, then usage, then scope. Every sentence adds value.

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, description covers usage, scope, and related tools. Could mention return format or error handling, but overall complete for a simple retrieval tool.

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 100% coverage for the single 'key' parameter. Description adds semantic value by explaining omission lists all keys, which is not inferable from schema alone.

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 retrieves values saved via 'remember' or lists all keys when omitted. It distinguishes itself from sibling tools by naming them and defining its specific role.

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?

Explicitly says when to use (look up stored context) and how to use it (omit key for listing). Mentions scoping and pairing with remember/forget, providing clear alternatives.

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 must fully disclose behavior. It explains that the tool fans out to three external sources in parallel, returns structured changes with a count and citation URIs, and describes the 'since' parameter format. It does not cover rate limits or authentication, but for a query tool this is adequate.

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 paragraph with multiple sentences, front-loaded with a clear question. It is informative without being verbose, each sentence adds value. However, it could be slightly more structured with bullet points for the data sources or output format.

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 3 parameters with 100% schema coverage and no output schema, the description adequately explains the output (structured changes, total_changes count, citation URIs) and the data sources. It provides sufficient context for an agent to use the tool correctly, though it does not describe pagination or limits.

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 baseline is 3. The description adds value by explaining the 'since' parameter's accepted formats (ISO date or relative shorthand like '7d') and typical usage ('Use "30d" or "1m" for typical monitoring'), and notes that 'type' currently only supports 'company'. This provides useful context 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 the tool's purpose: answering 'what's new with a company' in a recent time window. It provides specific example queries like 'any updates on Y?' and 'news on Apple this month', and mentions the data sources (SEC EDGAR, GDELT, USPTO), distinctly differentiating it from sibling tools like entity_profile or compare_entities.

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 tells when to use the tool with example user queries, but does not specify when not to use it or mention alternatives among sibling tools. It provides clear context for usage, but lacks explicit exclusions or comparisons.

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 fully discloses that memory is key-value, scoped by identifier, with persistence details (24-hour retention for anonymous sessions, persistent for authenticated users). No contradictions. This is a 5.

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 with no wasted words. It front-loads the main purpose and usage in the first sentence, then efficiently provides additional context. Every sentence earns its place. This is a 5.

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?

The description is fully complete given the tool's simplicity and lack of output schema. It explains what the tool does, when to use it, how it works (key-value store, scoping, persistence), and how it relates to siblings. No gaps remain. This is a 5.

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 baseline is 3. The description adds value by providing concrete examples of key formats (e.g., 'subject_property', 'target_ticker') and clarifies that value is any text. This goes beyond the basic schema, earning a 4.

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's purpose with a specific verb ('Save') and resource ('data the agent will need to reuse later'). It distinguishes from sibling tools recall and forget by explicitly mentioning them. This is a 5.

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 provides explicit guidance on when to use this tool ('when you discover something worth carrying forward') and directs to alternatives ('Pair with recall to retrieve later, forget to delete'). It also explains scoping and persistence rules. This is a 5.

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 carries full burden. Describes that it returns IDs plus citation URIs, and implies safe read operation. No contradictions, no side effects disclosed, but adequate for a lookup tool.

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 paragraph, dense but clear. Every sentence adds value. Could be slightly more structured but remains readable and front-loaded with purpose.

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, but description mentions return type (IDs + citation URIs) and specific ID systems. Lacks exact structure but compensates with examples. Complete enough for effective 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 coverage is 100%, but description adds rich examples and context beyond schema (e.g., 'Apple' → AAPL, CIK 0000320193). Explains value formats for both parameters, greatly aiding correct usage.

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?

Clearly states it looks up canonical/official identifiers for companies or drugs, with specific ID systems (CIK, ticker, RxCUI, LEI). Differentiates from siblings by focusing on identifier resolution, not general entity profiles or comparisons.

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?

Explicitly says to use this before other tools needing official identifiers, with examples. Could improve by clarifying when not to use it or naming alternatives, but current guidance is strong.

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?

Annotations indicate read-only, open-world, idempotent, non-destructive. Description adds behavioral context: probes each entity, ranks results, returns ranked list with score, confidence, signal density. 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.

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

Three sentences, front-loaded with purpose, then method, then use case. No wasted words. Every sentence adds value.

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?

With no output schema, description adequately explains return structure (ranked list with score, confidence, signal density). Covers inputs (entities, models, apikey, context). Could mention pagination or limit details, but sufficient for typical 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 100%. Description reiterates that first entity is treated as subject, but this is already in schema. Does not add new semantics beyond schema details. Baseline score of 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?

Description clearly states it compares AI visibility across multiple entities, probes each with ai_visibility_check, ranks by score, and identifies most/least recognized. Provides a concrete use case example ('does Claude know about us as well as our competitors?'). Distinguishes from sibling ai_visibility_check which is a single probe.

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?

Explicitly states usage context: 'competitive AI-marketing audits'. Provides an illustrative question to guide when to use. Lacks explicit when-not to use, but context implies preference over single entity probe. No explicit alternative named for non-competitor comparisons.

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?

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. Description adds valuable context: fans out to two services, partial failures degrade gracefully, bundlephobia first measurement latency (5-30s), sources_failed list. No contradiction 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.

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

Description is lengthy but front-loaded with the main purpose. Every sentence earns its place, explaining composite nature, return format, and fallbacks. Could be slightly tighter but effective.

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, but description enumerates return fields and explains edge cases (partial failures, latency). High complexity tool, description covers all important aspects 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.

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

Schema coverage is 100%, so baseline is 3. Description adds minor extra: scoped packages accepted, version defaults to latest. The schema already documents these. No significant added meaning 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's a composite check for npm packages covering license, advisories, version history, and bundle size. It distinguishes from deps.dev:version for other ecosystems and from sibling tools like scan_competitor_ai_presence or weather_now.

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?

Explicitly says 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. Also mentions limitations: NPM only in v1, fallback for other ecosystems via deps.dev:version. Provides clear when-to-use guidance.

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 carries the full burden of behavioral disclosure. It merely states the action without explaining response format, pagination behavior, rate limits, or authentication needs. Basic 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.

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

The description is a single sentence, efficiently stating the tool's purpose. It is front-loaded with the core action. However, it is too brief to cover needed behavioral context, but for conciseness it earns a 4.

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, the description should explain return values (e.g., list of datasets, metadata). It does not. Also, sibling tools exist but no differentiation is provided. The description is incomplete for a search tool with three parameters.

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 100%, so all parameters are documented in the input schema. The description adds no additional meaning beyond what the schema already provides (e.g., page, query, page_size). 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 'Browse / search the data.gov.sg dataset catalog' clearly states the tool's function and resource. It distinguishes from siblings like get_dataset (specific dataset retrieval) and query_dataset (querying data within datasets), making its purpose 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.

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

While the description implies use for browsing or searching, it provides no explicit guidance on when to use this tool versus alternatives like get_dataset or query_dataset. No 'when-to-use' or 'when-not-to-use' instructions are given.

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, description must disclose behavior. Only mentions 'live' but omits update frequency, data format, or limitations.

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?

Extremely concise (5 words). Could benefit from a sentence structure, but no excess verbiage.

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, description should explain what 'positions' means (coordinates? addresses?) and typical usage. Currently insufficient for agent to interpret results.

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?

No parameters exist (schema coverage 100% for empty properties), so baseline 4 applies. Description adds no param detail but none needed.

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?

Clearly states resource ('taxi positions') and scope ('live', 'across Singapore'). Verb is implied. No sibling confusion since siblings cover different domains.

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 on when to use this tool vs alternatives. Even with no similar siblings, a note on context (e.g., real-time query) would help.

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 exist. Description lacks information about data source, update frequency, or what 'current' means (e.g., real-time vs. last 5 minutes). For a tool with no params, it should provide 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.

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

Single sentence, front-loaded, no redundant words. Perfectly concise.

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, description only says 'current incidents'. It doesn't explain output format, incident details, or update frequency. For a simple tool it is adequate but leaves questions.

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?

Input schema has zero parameters (coverage 100%). Baseline for 0 params is 4. Description adds no extra parameter info, but none is needed.

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 the resource (incidents on expressways and major roads) and implies retrieval. It distinguishes from siblings by topic, but could be more active (e.g., 'Retrieve' instead of 'Current incidents').

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 on when to use this tool versus alternatives. While it's simple with no parameters, there is no mention of when to choose it over other tools like taxi_availability or weather_now.

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 should disclose behavioral details like data source, update frequency, or whether location is inferred. It only states 'Current UV index' with no elaboration.

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 extremely short (three words) and front-loaded, but it is a noun phrase rather than a complete sentence, which may reduce clarity for an agent.

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 no parameters, no output schema, and low complexity, the description is minimally adequate but lacks details like return format or unit of measurement.

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 no parameters, and schema coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond the empty 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 that the tool returns the current UV index, which is a specific resource. It differentiates from sibling tools like weather_now or air_quality_* by focusing on UV index.

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 such as weather_now or air_quality tools. There is no context about location or time dependencies.

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 that the tool returns a verdict with five possible values, a structured form, actual value with citation, and percent delta. Also notes that it consolidates 4-6 sequential calls, indicating efficiency. However, it does not explicitly state the tool is read-only or discuss authorization/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?

Description is four sentences, front-loaded with purpose, followed by usage context, scope details, and output summary. Every sentence adds essential information with no redundancy. Efficiently communicates all key aspects.

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 only one parameter, no nested objects, and no output schema, the description thoroughly explains input expectations and output structure. It covers supported claim types, verdict categories, and integration value, making the tool self-contained for agent decision-making.

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?

With 100% schema description coverage, baseline is 3. The description adds value by providing example claim formats ('Apple's FY2024 revenue was $400 billion') and explaining the natural-language nature, which aids an agent in constructing valid input beyond the schema's basic string definition.

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?

Clearly states the tool's function (fact-checking factual claims) and specific domain (company-financial claims via SEC EDGAR + XBRL). The description distinguishes it from sibling tools, which are mostly unrelated (air quality, traffic, etc.), and highlights that it replaces multiple sequential calls, reinforcing its unique purpose.

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?

Provides explicit when-to-use guidance with example queries ('Is it true that…?'). Describes the supported claim type (company-financial) and mentions scope limitations, which helps agents decide applicability. Lacks explicit 'when not to use' or alternative tool references, but the sibling set is diverse enough that the context is sufficient.

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 should disclose behavioral traits like data freshness, caching, or rate limits; it only states the data categories, offering 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.

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

The description is a single concise sentence with no wasted words, front-loading the key information about what the tool returns.

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's simplicity (no parameters, no output schema), the description provides the core purpose but lacks details on data source, update frequency, or output format, leaving some context incomplete.

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 has zero parameters, so the description does not need to add parameter details. It implicitly suggests no input is required, which is sufficient.

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 provides current temperature, humidity, wind, and rain across Singapore weather stations, distinguishing it from sibling tools like air_quality_pm25 and uv_index.

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 for current weather data but lacks explicit guidance on when or when not to use this tool compared to related tools (e.g., air quality or UV).

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