Owid

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

Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) are already present. The description adds value by detailing return structure ({score, confidence, signals, raw_response}), cost implications (BYO key for Anthropic), and default model behavior.

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, about 100 words, front-loaded with main action and key details. Every sentence adds meaningful information with no waste.

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 explains the return format and combined view. All necessary behavioral context (defaults, costs, usage) is provided, making the tool fully usable by an agent.

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 good descriptions for all parameters. The tool description reinforces usage of `_apiKey` and `models` with practical context (free default, BYO key), adding value 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 probes LLMs for knowledge about an entity and scores visibility 0-100 per model. It names the default model and optional Anthropic probing, distinguishing it from siblings like scan_competitor_ai_presence.

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 mentions use cases (AI-marketing audits, pre-launch checks, competitive monitoring) and gives context on default vs. paid model usage. Does not explicitly exclude alternatives or mention when not to use, but context is clear.

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

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

No annotations provided, so description fully responsible. Describes selection and argument filling, but omits behavior for ambiguous queries or failures. Examples help, but limitations 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?

Highly concise (three sentences plus examples), front-loaded with purpose, no waste.

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?

Sufficient for a simple meta-tool with one parameter and no output schema. Provides examples and clarifies orchestration, though lacks error handling details.

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 already covers the single parameter with description. Description adds 'plain English' context and examples, enhancing 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?

Description clearly defines the verb 'ask' and resource 'question', with explicit distinction from sibling tools like 'discover_tools' and 'fetch_indicator' by stating it orchestrates multiple 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?

Provides clear guidance: 'No need to browse tools or learn schemas — just describe what you need.' Implies usage when unsure which tool to select, but lacks explicit when-not or 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?

Annotations indicate read-only, open-world, non-destructive behavior. The description adds context about resolving markets, classifying bets, and fanning out to data packs, aligning with annotations and providing further behavioral details.

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

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

The description is concise (3-4 sentences) with front-loaded primary purpose, followed by input formats and output summary. Every sentence adds value with no redundancy.

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

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

Despite no output schema, the description clearly states what is returned (evidence packet and market-vs-model comparison). Given the tool's moderate complexity and high schema coverage, the description is complete enough for correct invocation.

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 enhances the schema by explaining that 'market' can be a slug, URL, or question text, and 'depth' enum values 'quick' and 'thorough' with their meanings. This adds significant value beyond the schema's 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 researches Polymarket bets using Pipeworx data, with specific inputs (slug, URL, question text) and outputs (evidence packet, market-vs-model comparison). It distinguishes itself from sibling tools by being specialized for betting research.

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?

Explicit usage cues like 'Use for 'should I bet on X?'' and 'agents that get bet-relevant context here convert better' provide clear guidance on when to use this tool versus 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?

With no annotations, the description carries full burden. It discloses return data (paired values, URIs) and sources (SEC EDGAR, FDA). It does not mention destructive actions, aligning with a read-only 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 concise sentences front-load the core function, include key details, and avoid redundancy. 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?

The tool lacks an output schema, so the description must explain return values. It mentions 'paired data' and 'resource URIs' but could detail the structure more. However, it is sufficient for common use cases.

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%. The description adds value beyond the schema by explaining type-specific fields and providing examples, aiding correct parameter construction.

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 'Compare' and the resource 'entities', with specific data fields for each type. It also highlights the efficiency gain over sequential calls, leaving no ambiguity about the tool's 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?

The description implicitly advises use when comparing 2-5 entities and replaces 8-15 sequential calls, but lacks explicit when-not-to-use guidance or named alternatives among 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 provided; description states it returns tool names and descriptions but doesn't disclose read-only nature or other behavioral traits beyond the obvious search functionality.

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 sentences, each valuable: first defines purpose, second gives usage guidance. 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?

Adequately covers return value (tool names and descriptions) and usage context. Could mention pagination or ordering, but sufficient for a simple search 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?

Input schema has 100% coverage with clear descriptions for both parameters. Description doesn't add new parameter information beyond what 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?

Clearly states it searches the Pipeworx tool catalog by natural language, and returns relevant tools with names and descriptions. Differentiates from siblings like ask_pipeworx which is for questions.

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 'Call this FIRST when you have 500+ tools available and need to find the right ones.' Provides clear context but doesn't explicitly state when not to 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?

No annotations provided, so description carries full burden. It discloses that the tool bundles 10–15 data sources, returns pipeworx:// citation URIs, and lists specific data types. It does not mention error handling or rate limits, but the detail is sufficient for a read-like operation.

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 wasted words. First sentence states purpose, second lists return content, third provides an alternative. All information is front-loaded and easy to parse.

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 that returns a composite profile with no output schema, the description explains what the return value contains (citation URIs) and covers constraints, alternatives, and capabilities. No important gaps remain.

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 significant meaning: explains that only 'company' is supported (with hints about future types), specifies value formats (ticker or CIK), and clarifies that names are not supported, recommending a different tool. This goes well beyond the schema's basic description.

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 a full profile of an entity across multiple Pipeworx packs in one call. It specifies data types for company type (SEC filings, revenue, patents, news, LEI) and distinguishes from sequential calls and alternatives like usa_recipient_profile.

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 (for full entity profile) and when not to (federal contracts). Also provides guidance that names are not supported and suggests using resolve_entity first.

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, so description carries full burden. States return format and optional country filter, but omits limits, error handling, or pagination. Adequate but not extensive.

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. Efficiently communicates core purpose, return format, and optional filters. No fluff.

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 specifies return shape ({entity, year, value}). Covers slug examples and country filter details. Missing error/empty handling 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?

100% schema coverage. Description adds that country filter accepts ISO codes or names (beyond schema). Also confirms default limit of 5000, which matches schema. Adds value.

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 uses specific verb 'Fetch' with clear resource 'tidy long-format data for an OWID indicator by slug' and examples. Distinguishes from siblings like get_indicator_metadata and list_popular_indicators.

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?

Implies use for fetching data vs metadata, but no explicit when-to-use or when-not-to-use. References browsing slugs elsewhere for discovery.

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, and the description lacks details on permanence, side effects (e.g., what happens if key doesn't exist), or confirmation requirements. For a destructive operation, more disclosure is needed.

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

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

The description is a single, front-loaded sentence with no wasted words. Highly 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 simple single-parameter delete tool without an output schema, the description is mostly complete. It misses behavioral context but covers the core purpose 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 input schema has 100% description coverage for the key parameter, so the description adds minimal additional meaning. 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 action 'delete' and the resource 'stored memory', with the required key parameter. It distinguishes from sibling tools like 'recall' and 'remember'.

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 deleting memories, but provides no explicit when-to-use or when-not-to-use guidance compared to 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?

Annotations (readOnlyHint=true, idempotentHint=true) are consistent. Description adds behavioral context: fetches page, extracts metadata, emits standard format. Does not mention potential errors or rate limits, but adequate for a simple read tool.

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

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

Two concise sentences plus a bulleted list of use cases. Every sentence adds value; no fluff. Front-loaded with action and output.

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 simplicity (2 params, no output schema, rich annotations), description covers purpose, output format, and use cases. Could mention accessibility prerequisites or error scenarios, but not critical.

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 implicitly uses the 'url' parameter but does not add meaning beyond the schema. 'max_links' is not mentioned in the description, relying on schema description.

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 tool generates an llms.txt file for a given URL, specifying the output format (standard markdown) and use cases. It distinguishes from siblings like 'scan_competitor_ai_presence' by focusing on a specific deliverable (llms.txt).

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 clear use cases: getting a client's site indexed, drafting for own project, auditing competitor AI visibility. Does not explicitly state when not to use or alternatives, but 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?

No annotations are provided, so the description must carry the burden. It describes a read operation without side effects, which is appropriate. However, it does not disclose any potential rate limits, authentication requirements, or error conditions, leaving some behavioral gaps.

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, consisting of two sentences. The first sentence clearly states the function and what is returned. The second sentence adds a usage hint. No unnecessary 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 there is no output schema, the description adequately explains what the tool returns (title, subtitle, units, sources, last updated). It also provides a usage context. It is nearly complete for a simple metadata 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?

The input schema has 100% coverage with a description for the 'slug' parameter as 'OWID chart slug'. The description adds context on why you might use it ('verify the slug'), but does not enhance the semantic meaning beyond what the schema already 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 the tool fetches metadata for an OWID indicator, listing specific fields like title, subtitle, units, sources, and last updated. It hints at differentiation from a potential 'fetch' tool by noting 'Helpful before fetching to verify the slug', though does not explicitly name alternatives.

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

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

The description provides a specific use case: use this tool before fetching data to verify the slug. However, it does not explicitly state when not to use it or mention alternative tools for other purposes.

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; description discloses curation and non-exhaustiveness but lacks details on idempotency, pagination, or other behavioral traits for a read-only list.

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: first states main action, second tells how to use output, third sets expectations. Efficient 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?

For a tool with one optional parameter and no output schema, the description sufficiently covers purpose, return format (slug + title), usage direction, and limitations.

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 merely restates 'optional category filter' from schema, adding no extra meaning beyond what the enum already 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?

Description clearly states it lists curated indicators for common categories with slug and title, and explicitly connects to fetch_indicator, distinguishing it from 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?

Directs to use the slug with fetch_indicator and notes the list is not exhaustive, but does not explicitly exclude alternative tools or provide when-not-to-use guidance.

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

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

Discloses rate limit (5 messages/identifier/day) and states 'Free'. No annotations exist, so description carries full burden; additional details on privacy or acknowledgment would improve.

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?

Four concise sentences, front-loaded with purpose. No wasted words, structured for quick parsing.

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 simple feedback nature, description fully covers purpose, usage, rate limits, and content guidelines. Complete for agent invocation.

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 detailed descriptions for all parameters. Description does not add much parameter-level info but is not necessary; baseline score applies.

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 sends feedback to Pipeworx team, enumerates specific use cases (bug reports, feature requests, missing data, praise), and distinguishes from sibling tools like ask_pipeworx.

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 and guidance on content (describe tried tools, avoid verbatim prompts). Mentions rate limit, but does not explicitly exclude cases like asking questions (sibling tool exists).

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 safe read-only behavior. The description adds valuable context: data source (CF analytics-engine), no PII, and caching window (5min-1h), which goes beyond the 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 with no wasted words: first sentence states core output, second lists use cases, third adds technical provenance. Front-loaded and 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?

With no output schema, the description adequately describes what is returned (top tools, packs, call volume) and how it works. Sufficient for an agent to understand behavior and integration, though exact structure is omitted.

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 a described enum. The description adds interpretive guidance for the window parameter ('shorter windows surface what's hot; longer show steady-state'), which adds 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 the tool returns 'top tools, top packs, and total call volume' with specified time windows, distinguishing it from siblings by focusing on what other AI agents are calling right 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?

Three explicit use cases are provided: discovering hot data sources, confirming canonical choice, and aligning use cases. This gives clear context for when to use the tool, though no explicit when-not scenarios 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?

The description adds behavioral context beyond annotations: it details the output (ranked opportunities with direction and reasoning) and explains the internal logic (monotonicity checks). Annotations already indicate read-only and non-destructive nature, so the description complements them well.

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 (~5 sentences) with clear structure: two modes highlighted using headings. Every sentence adds value, and the length is appropriate for the complexity.

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 absence of an output schema, the description explains the return format (ranked opportunities with reasoning). It covers inputs, modes, and logic, making the tool fully understandable.

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 description explains the role of each parameter: 'event' triggers single-event mode, 'topic' triggers cross-event mode. Examples are provided, adding significant meaning beyond the schema's brief 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 finds arbitrage opportunities via monotonicity violations. It distinguishes two modes (event and topic) and explains their differences, making the purpose unambiguous and distinct from 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 explicitly explains when to use each mode: event for a single event slug, topic for cross-event searches. It gives a concrete example of when cross-event mode is necessary ('May≤June rule'), providing clear guidance on tool selection.

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 readOnly and non-destructive. Description adds behavioral details: uses lognormal model from FRED + coinpaprika, groups by asset, fetches price history once, ranks by |edge|. No contradictions.

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

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

Four sentences with focused information: purpose, model details, processing steps, and intended use. Efficient without unnecessary fluff.

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, description explains return structure (top N with edge and direction). Covers data sources, model, and default behavior. Adequate for an agent to understand tool's capability.

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. Description provides default values (limit=10, window='1wk', min_edge_pp=0.5) not in schema, adding useful context beyond parameter names.

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 tool scans Polymarket markets, identifies where Pipeworx data disagrees with market price, and returns top N edges with trade direction. It distinguishes from sibling tools like polymarket_arbitrage by focusing on edge 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?

Explicitly states the use case: 'what should I bet on today' and discovering opportunities without manual browsing. No explicit when-not or alternative tools mentioned, but context is clear.

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

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

Annotations indicate readOnly, openWorld, idempotent, and non-destructive behavior. The description adds value by explaining the typical price delta (2-25pp), the return format (leg-by-leg prices in 0-1 range and spread in percentage points), and how parameters override topic mappings. 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?

The description is concise yet comprehensive: it states purpose, explains the arb signal, describes two modes with examples, and specifies the output format. Every sentence is informative, with the key behavioral traits 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 no output schema, the description fully specifies return values (leg-by-leg prices and spread). It covers all three parameters, explains both usage modes, and contextualizes the tool within its venue-specific domain. No gaps for an agent to infer.

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 each parameter having its own description. The description adds meaning by explaining that 'topic' is a shortcut that auto-fetches matching events, and that explicit parameters 'override the topic-mapped side.' This enriches the schema information.

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 and resource: 'Cross-venue spread between Kalshi and Polymarket for the same resolving question,' distinguishing it from sibling tools by naming the specific venues and calling it an 'arb signal.' It explicitly describes two operation modes, making the tool's purpose unmistakable.

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 clearly outlines two modes ('topic' for pre-mapped shortcuts vs explicit parameters) and explains when to use each. While it doesn't explicitly list when not to use the tool or provide alternatives, the mode guidance is sufficient for an AI agent to select correctly given sibling tools like 'polymarket_arbitrage' 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?

No annotations provided, so description carries full burden. Describes the dual behavior (retrieve by key or list all) but does not detail return format, error handling, or persistence scope.

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 sentences, front-loaded with action, no wasted words. Efficient and clear.

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 simple parameters, the description adequately explains functionality and usage. Could mention return format but not necessary for a 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 coverage is 100% with a description for the 'key' parameter. The tool description adds minimal extra value beyond the schema, mainly reinforcing the omit-to-list behavior.

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 a memory by key or lists all memories, with specific verb and resource. It distinguishes from sibling tools like 'forget' and 'remember'.

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 this to retrieve context you saved earlier', providing clear when-to-use context. Does not explicitly state when not to use, but alternatives are implied by 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?

With no annotations provided, the description carries the full burden and effectively discloses key behaviors: parallel fan-out to multiple sources, accepted since formats (ISO date or relative), and return structure (structured changes, count, URIs). It does not mention potential delays or rate limits but provides substantial behavioral insight.

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, front-loading the purpose and following with details. It is concise without unnecessary words, though a more structured format could improve readability.

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 explains the return format (structured changes, count, URIs) and covers the primary use case. However, it could provide more detail on the structure of changes or how to interpret results across sources.

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 description adds value beyond the schema: for 'since', it provides examples and a recommendation for typical monitoring; for 'type', it clarifies the current limitation; for 'value', it specifies accepted formats. This enriches the parameter understanding.

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: 'What's new about an entity since a given point in time' and details the specific behavior for the only supported type (company), including fan-out to SEC, GDELT, and USPTO. This distinguishes it from sibling tools like entity_profile and 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 says 'Use for brief me on what happened with X or change-monitoring workflows,' providing clear usage context. While it does not explicitly mention when not to use or name alternatives, the context implies appropriate use cases.

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?

The description discloses important behavioral details: the persistence difference between authenticated (persistent) and anonymous (24-hour) sessions. This adds value beyond the input schema. However, it does not mention overwrite behavior or whether the operation is idempotent, but given the absence of annotations, it covers key aspects.

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. It front-loads the core action ('Store a key-value pair') and uses efficient phrasing throughout.

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 (2 params, no output schema, no nested objects), the description is reasonably complete. It covers the storage duration and persistence difference. It could be more thorough by mentioning overwrite behavior, but overall it 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?

The input schema has 100% coverage with clear descriptions for both parameters ('key' and 'value'). The description does not add any additional semantic information beyond what is already in the schema, so the baseline score of 3 applies.

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

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

The description clearly states it stores a key-value pair in session memory, with a specific verb ('store') and resource ('session memory'). It distinguishes itself from siblings like 'recall' and 'forget' by focusing on storage, not retrieval or deletion.

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 says 'Use this to save intermediate findings, user preferences, or context across tool calls,' providing clear usage context. However, it does not explicitly mention when not to use it or name alternative tools for related operations (e.g., 'recall' for retrieval).

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. It explains that the tool returns canonical IDs and pipeworx:// URIs, supports two entity types, and operates in a single call. It does not mention error handling or limitations, but the core behavior is clearly disclosed.

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 concise sentences that front-load the purpose, each sentence adding value without redundancy. 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 simple lookup tool with two parameters and no output schema, the description covers purpose, input format, supported types, return content, and efficiency benefit. It is fully 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?

Schema coverage is 100%, but the description adds valuable examples (e.g., 'AAPL', '0000320193', 'ozempic') and clarifies the input format for both types, going 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 clearly states the verb 'Resolve', the resource 'entity to canonical IDs', and the scope 'across Pipeworx data sources'. It distinguishes between company and drug types, making it specific and distinct from siblings like 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 implies when to use the tool by stating it 'Replaces 2–3 lookup calls' and describes the supported entity types, but does not explicitly exclude alternative tools or provide when-not-to-use guidance.

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

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

Annotations already provide readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false. The description adds behavioral context: it probes each entity with ai_visibility_check, ranks by score, and surfaces which is most/least recognized. This goes beyond annotations but does not detail the ranking algorithm or error handling.

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 3-4 sentences, front-loaded with the main purpose ('Compare AI visibility across multiple entities side-by-side'), and each sentence adds value. There is no redundancy or unnecessary 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?

Despite no output schema, the description clearly states the return format: 'ranked list with score, confidence, signal density per entity.' All four parameters are explained in the schema with 100% coverage, and the description provides sufficient context for an agent to use the 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?

Input schema has 100% description coverage (baseline 3). The description adds meaning by noting that the first entity in the array is treated as the 'subject' for narrative purposes, which is not in the schema. This additional context justifies a score above baseline.

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 compares AI visibility across multiple entities side-by-side, using a specific verb 'Compare' and specifying the resource 'AI visibility'. It distinguishes itself from sibling 'ai_visibility_check' by focusing on comparison rather than 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?

The description explicitly mentions usefulness for competitive AI-marketing audits and gives an example question ('does Claude know about us as well as our competitors?'). However, it does not explicitly state when not to use this tool or suggest alternatives, though the sibling context implies a single-check alternative.

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?

Beyond annotations (readOnly, idempotent, not destructive), the description adds key behavioral details: partial failures degrade gracefully, bundlephobia first measurement can take 5-30s, and sources_failed will list timeouts. No contradictions.

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

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

Three sentences, front-loaded with the composite nature. Dense but every sentence provides value. 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?

Despite no output schema, the description fully explains return values (summary block, advisory detail, links, alternative versions), failure handling, and ecosystem scope. Complete for the tool's complexity.

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 description adds little extra for parameters beyond noting that version defaults to latest. Adequate but not enhanced.

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 npm package evaluation tool, covering license, advisories, version history, and bundle size. It uses specific verbs ('scan', 'fans out') and resource ('npm package'), and distinguishes from siblings by being a single-call composite check.

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 (e.g., 'is X safe / popular / small') and when not to (NPM ecosystem only; other ecosystems fall under deps.dev directly). Provides clear 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 full burden. It discloses the tool is non-destructive (a fact-check), lists return values (verdict, structured form, actual value with citation, percent delta), and explains it replaces multiple agent calls. It could mention potential errors or limitations (e.g., only v1, specific data sources), but overall it is transparent.

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 the main purpose, followed by details on supported domains and return values. No unnecessary words; every sentence adds value.

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

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

Given one simple parameter and no output schema, the description adequately explains the tool's purpose, supported domain, and return format. It could mention limitations (e.g., only US public companies, financial metrics only) but these are implied by 'v1 supports'. Overall, it provides sufficient context for an agent to use correctly.

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

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

Schema coverage is 100% for the single parameter 'claim'. The description adds value by providing examples of natural-language claims and explaining the return values, which gives context beyond the schema alone. Baseline 3 is increased due to the helpful examples and explanation of output.

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 action ('fact-check a natural-language claim against authoritative sources'), specifies the supported domain ('company-financial claims...public US companies'), and lists the return types (verdict, actual value, citation, percent delta). It also distinguishes itself from siblings by noting it replaces 4–6 sequential agent calls.

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 states the supported domain (company-financial claims for public US companies) and what the tool returns. It implies when to use it (for factual claims in that domain) but does not explicitly state when not to use it or mention alternatives like using sequential calls for other domains.

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