Coinbase Exchange

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

The description discloses behavioral traits beyond annotations: default model is free, passing _apiKey probes Anthropic with direct payment, and output includes per-model {score, confidence, signals, raw_response} plus combined view. It does not contradict any annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint).

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, well-structured paragraph of 69 words. It front-loads the main purpose, then details default model and API key, then output, then use cases. Every sentence adds value without 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 compensates by detailing return structure. It covers parameters, usage, and limitations (e.g., _apiKey required for Anthropic). The tool is straightforward, and the description is complete 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 the description adds meaning by explaining the entity parameter's scope, models parameter's defaults and required key, _apiKey's direct pass-through, and context's disambiguation purpose. It also describes the output fields not in 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: 'Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model.' It identifies a specific verb 'probe', resource 'LLMs', and subject domain, distinguishing it from siblings like 'scan_competitor_ai_presence' which focus on different aspects.

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 clear use cases: 'Useful for AI-marketing audits, pre-launch brand checks, competitive monitoring.' It implies when to use this tool, but does not explicitly exclude alternatives or state when not to use it, lacking explicit comparison to 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds valuable context: routes to 4,862 tools across 1,272 sources, returns structured answer with citation URIs, and works on all tiers. No contradiction.

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 front-loaded priority guidance, explicit examples, and organized alternatives. Slightly verbose but every sentence adds value. Could be trimmed marginally but remains 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 the tool's complexity (4862 tools, many use cases), the description is comprehensive: covers purpose, usage context, examples, alternatives, and limitations. Return values are implied (structured answer with citations) even without output 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% with aliases documented. Description does not add further parameter semantics beyond what schema provides; baseline 3 is appropriate as schema already does the heavy lifting.

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 factual questions using authoritative structured data from many sources, with specific verb 'ask' and resource 'Pipeworx'. It distinguishes from siblings like ask_pipeworx_grounded and deep_research by providing use-case boundaries.

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 advises 'PREFER OVER WEB SEARCH', gives when-to-use criteria (e.g., 'what is', 'look up', factual questions), and specifies alternatives for hallucination-resistant (ask_pipeworx_grounded) or broad queries (deep_research). Also says 'START HERE' as default entry point.

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 readOnly, openWorld, idempotent, non-destructive. The description adds valuable context: extra LLM call cost, explicit refusal reasons on failure, and output format details (answer, evidence, etc.). 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 informative and well-structured, front-loading the core purpose. While slightly longer than minimal, every sentence contributes useful information (alternatives, return format, refusal reasons). 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?

The description fully covers the tool's operation, output, failure modes, and trade-offs. Given the complexity (6 params, no output schema but detailed description), it is complete and leaves no ambiguity.

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% (all parameters documented with aliases). The description does not add additional parameter semantics beyond the schema, which is acceptable. 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 tool's purpose: 'Hallucination-resistant answer mode for high-stakes reads.' It explains the mechanism (picks tool, fetches data, extracts answer) and distinguishes from sibling 'ask_pipeworx' by highlighting the extra cost and use case.

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 guidance on when to use: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts.' Also provides exclusion: 'prefer ask_pipeworx for casual lookups.' Clear alternatives 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?

Annotations already declare readOnlyHint and idempotentHint. The description adds extensive behavioral details: resolution outcomes (low_confidence_match, market_closed_or_inactive), fan-out behavior per category, safety checks, response shapes, and cancellation rule parsing. 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 long but well-structured with clear sections (classifiers, fan-out examples, response shapes, resolver contract, safety). Starts with core purpose. Some redundancy (e.g., repeated mention of low_confidence_match), but each paragraph serves a 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?

Despite no output schema, the description thoroughly covers all response fields (result.market, analysis, evidence), resolution logic, parent event extraction, news fallback, and edge cases. Complete for a complex tool with multiple data sources and outcomes.

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%, baseline 3. Description adds meaningful context beyond schema: explains that market input can be slug, URL, or question text; depth parameter distinguishes quick vs thorough; include_raw explains why false is recommended. Adds value effectively.

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 by pulling Pipeworx data. It distinguishes itself from sibling tools like polymarket_edges or validate_claim by focusing on a single bet research with evidence packet and market-vs-model comparison.

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 for "should I bet on X", "what does the data say about Y", or "is there edge in Z"'. Provides clear usage context but does not explicitly mention when not to use or list 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 already declare readOnlyHint=true, openWorldHint=true, etc. The description adds valuable behavioral context: data sources (SEC EDGAR, FAERS), handling of off-calendar fiscal years, and that results are sorted by primary metric. It does not contradict 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 relatively long but efficiently front-loaded with trigger phrases and covers all key points without redundancy. It packs many details (data sources, handling edge cases) without being verbose.

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

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

Given no output schema, the description explains return value (paired data + citation URIs) and covers use cases, limitations (2-5 entities, types), and data sources. It is fully adequate for an agent to understand the tool's capabilities and 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?

Schema coverage is 100% with 2 parameters. The description adds meaning beyond the schema by explaining what each type pulls (e.g., 'company pulls LATEST 10-K revenue + net income + cash + long-term debt') and gives valid input examples (tickers/CIKs for company, names for drug). This enhances the baseline 3.

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 performs side-by-side comparisons of 2-5 companies or drugs, using specific data sources (SEC EDGAR for companies, FAERS for drugs). It distinguishes itself from sibling tools like entity_profile by emphasizing that it replaces multiple sequential lookups.

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 advises 'ALWAYS PREFER over sequential single-pack lookups when comparing entities' and provides example trigger phrases like 'which is bigger' and 'rank these companies'. It implicitly tells when not to use: for single entity lookups. Could be more explicit about when not to use, but the 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, fully covering the safety profile. The description adds no behavioral context beyond these annotations, which is acceptable for a simple list 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?

The description is extremely concise at two words, 'List currencies.' Every word is necessary, and there is no wasted content.

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 parameters and the presence of an output schema, the description is complete enough. It clearly states the tool's function without requiring additional 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?

There are no parameters, so the baseline score is 4 per the rubric. The description does not need to add meaning beyond the schema since there is no schema to compensate for.

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 'List currencies' specifies a clear verb+resource combination. It distinguishes from the sibling tool 'currency' (singular), which likely retrieves a specific currency, making the purpose 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?

The description provides no explicit guidance on when to use this tool versus alternatives. While it is implied that this tool lists all currencies, there is no exclusion or context for when a different tool might be more appropriate.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description 'Single currency.' adds no behavioral context beyond annotations, missing an opportunity to describe what data is returned.

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 but omits essential information. Conciseness requires informativeness; this is under-specification.

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 having an output schema, the description fails to indicate that this tool retrieves details about a single currency, making it incomplete for the given 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?

With 0% schema description coverage, the description should explain the currency_id parameter but does not. Examples show 'BTC' and 'USD' but no explanation of format or values.

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 'Single currency.' is a tautology that restates the name without adding a verb or resource. It fails to distinguish from siblings like 'currencies' and does not explain what the tool does.

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 usage context, exclusions, or alternative tools are mentioned. The description provides no 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?

Detailed disclosure of behavior: returns findings packet with verbatim evidence, confidence, source, citation, gaps[], hop field, contradictions for thorough. Expected time ranges. Annotations (readOnlyHint=true, etc.) are consistent; description adds 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?

Description is thorough but slightly long; however, critical info is front-loaded (account requirement, alternatives), and every sentence adds value. Could be slightly more concise but well-structured.

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?

Complete coverage given simple params (2 total, 1 required) and no output schema. Explains output format, multi-facet decomposition, parallel execution, depth behavior, and timing. Agent has all info needed 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% with descriptions. Description adds detailed explanation of depth levels (quick=3, standard=5, thorough=8) and their behaviors, enriching the enum values.

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 performs multi-source research over structured data, distinguishes from sibling tools like ask_pipeworx for single lookups or current news. Specific verb+resource with clear scope.

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 guidelines: when to use (broad/multi-part questions over structured data), when not (single lookup, current news), and alternatives (ask_pipeworx). Also mentions account requirement and that ask_pipeworx works without sign-in.

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 readOnlyHint=true and idempotentHint=true. The description adds that results are 'ready to call directly, no second schema lookup needed,' which is useful context beyond annotations. Overall, good transparency without contradiction.

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 core purpose, then domains, return format, and usage advice. 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?

Given no output schema and 6 parameters, the description explains what the tool returns (top-N tools with names, descriptions, schemas, examples) and how to use it effectively, providing complete context for 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%, so baseline is 3. The description adds value by listing aliases (task, q, description, search) and providing examples of natural language queries, which helps an agent understand how to use the 'query' parameter.

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

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

The description specifies the tool's purpose clearly: 'Find tools by describing the data or task.' It lists many domains and explains it returns top-N relevant tools with full schemas, distinguishing it from sibling tools that are specific search functions.

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 guidance: 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This tells when to use and implies when not to, making it very helpful for an AI agent.

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 readOnlyHint, openWorldHint, idempotentHint, and non-destructive. Description adds valuable behavioral context: fans out across multiple APIs in one parallel call, returns specific fields, and notes patent soft-fail. 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 a single dense paragraph but front-loaded with example queries. Every sentence adds value, though it could be slightly more structured with bullets. Overall efficient and informative without being overly verbose.

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

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

Given no output schema, description details return fields (cik, company_name, recent_filings with URIs, fundamentals, patents, news, LEI) and limitations. Covers enough for an agent to understand the tool's capabilities and outputs.

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 covers both parameters with descriptions; 100% coverage. Description reinforces with examples (ticker 'AAPL', CIK '0000320193'), clarifies that only 'company' type is supported, and emphasizes names are not accepted. Adds practical guidance 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 states tool provides a full cross-source profile of a US public company in one parallel call, listing specific data sources and fields such as SEC EDGAR, XBRL, USPTO, news, and GLEIF. It distinguishes itself from chaining other tools and from sibling tool 'resolve_entity' by noting that names are not supported.

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 advises to prefer this tool over chaining single-pack lookups for a holistic view. Provides clear when-to-use (user asks for a holistic view) and when-not-to-use (only names available; use resolve_entity first). Also mentions soft-fail for patent data due to API sunset.

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 declare destructiveHint=true and idempotentHint=true. Description adds context about clearing 'sensitive data', implying irreversibility, which enhances transparency without contradicting 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?

Two sentences, front-loaded with the action, no wasted words. Every sentence earns its place.

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?

Simple tool with one parameter and no output schema; description fully covers purpose, usage, and relationship to sibling tools. No 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% with a clear 'key' description. The description only adds 'previously stored', which is marginally helpful but not necessary 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?

Description clearly states 'Delete a previously stored memory by key', which is a specific verb+resource. It distinguishes from other tools by specifying 'memory' and references sibling tools 'remember' and 'recall'.

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 three scenarios ('context is stale, the task is done, or you want to clear sensitive data') and advises pairing with related tools, providing strong 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds behavioral details: fetches the page, extracts title/description/key links, and emits markdown. This provides context beyond annotations without contradiction.

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. The first sentence covers purpose and output, the second explains the process, and the third lists use cases. Information is 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?

Despite no output schema, the description explains the output format (standard llms.txt markdown) and deployment location. The tool has few parameters and straightforward behavior, so the description is 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%, so the schema already documents both parameters. The description adds minimal extra meaning (e.g., specifying URL type and example) but does not significantly improve understanding beyond the schema. Baseline score of 3 is appropriate.

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

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

The description clearly states the tool's verb ('Generate'), resource ('llms.txt file'), and scope ('for any URL'). It specifies the output format and use cases for AI crawlers, distinguishing it from sibling tools that might have broader or different purposes.

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 use cases (client sites, own projects, competitor auditing) but does not mention when not to use it or provide alternatives. Given the specific nature of the tool, the guidance is clear enough.

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, destructiveHint=false. Description adds return field details and parameter behavior (include_inactive) 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?

Two sentences, front-loaded key 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?

Despite no output schema, description lists return fields. Includes usage tip and parameter context. Fully sufficient for an agent to use correctly.

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

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

Schema coverage 100%, so baseline 3. Description mentions 'active' subscriptions, adding slight context to the parameter's default behavior, but does not significantly enhance 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?

Description clearly states 'List the caller's active subscriptions' with specific verb and resource, lists return fields, and distinguishes from sibling tools subscribe and unsubscribe.

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 guidance: 'Use this to review what you're monitoring before adding more or to find an id to cancel.' Could mention alternative tools like subscribe, but context 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 are all false, so the description carries full burden. It discloses that the tool is rate-limited (5 per identifier per day), free, and that feedback affects the roadmap. This provides rich behavioral context 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?

The description is well-structured and efficient. It front-loads the purpose, then lists use cases, instructions, and constraints. Every sentence adds value; there is no redundancy or unnecessary text.

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 all necessary aspects: purpose, usage, parameters, behavioral constraints, and limitations. Despite no output schema, it is complete for the tool's function.

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 meaningful detail: it explains the enum types with examples, advises on message length (1-2 sentences, 2000 chars), and clarifies that context is optional. This adds significant 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's purpose: to send feedback about bugs, missing features, or praise. It uses a specific verb ('tell') and resource ('Pipeworx team'), and distinguishes itself from sibling tools by focusing on feedback rather than queries or actions.

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 guidance for each feedback type (bug, feature, data_gap, praise). It also includes clear instructions on what not to do (don't paste end-user prompt) and mentions the tool is free and doesn't count against quota, helping the agent decide when to use it.

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

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

Goes beyond annotations by describing data source (CF analytics-engine, no PII), caching behavior (5min-1h depending on window), and aggregation nature. Also explains conceptual behavior: shorter windows for hot right now, longer for steady-state. Annotations already cover readOnly, openWorld, idempotent, non-destructive; description adds valuable 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?

Three sentences, each with clear purpose: output, use cases, data source/caching. No redundant or filler content. Front-loaded with key functionality. Appropriate length for a simple tool with one parameter.

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 (enum), no output schema, and complete annotations covering readOnly/idempotent, the description provides all necessary context: what is returned, how to interpret windows, data source, caching. No missing information about limits or pagination; tool is simple and self-contained.

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 description for 'window' parameter. Description adds semantic meaning about the effect of window choice: 'Shorter windows surface what's hot right now; longer windows show steady-state demand.' This provides guidance on parameter selection beyond the enum values and 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?

Description clearly states the tool returns top tools, packs, and volume over a window. Specific verb 'Returns', distinct resource 'top tools, top packs, total call volume'. Provides three specific use cases, distinguishing it from siblings like 'discover_tools' which may have different focus.

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 three useful scenarios for using the tool. Does not mention when not to use or directly compare to siblings, but the context of 'hot data sources' and 'canonical choice' provides clear guidance. Could be improved by noting when to use other tools like 'ask_pipeworx' instead.

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 declare readOnlyHint, openWorldHint, idempotentHint as true and destructiveHint as false. The description goes beyond by explaining internal logic: monotonicity checks, partition sum validation, semantic anchor (Jaccard similarity ≥0.30), partition filter, and fill check rationale. 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?

The description is thorough and well-structured, but somewhat lengthy. It efficiently front-loads the purpose and mode selection, then dives into technical details. While every sentence adds value, a slightly more condensed version could improve clarity without losing critical information.

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

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

Given the tool's complexity (two optional modes, no output schema), the description covers all key aspects: input options, internal algorithms, response fields (opportunities[], partition_check, fill_check), edge cases (placeholders, low similarity), and limitations (realizable edge ≤ 0). It is complete and self-contained.

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 descriptions are present but the tool description adds substantial meaning: explains what event does (walks child markets, checks ordering, partition_check) and what topic does (cross-event scanning, comparator on union). It also notes accepted URL formats and internal filtering 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 finds arbitrage opportunities on Polymarket using monotonicity violations and partition-sum checks. It distinguishes three modes: default trending_scan, event mode, and topic mode, each with specific use cases. This differentiates it from sibling tools like polymarket_edges and polymarket_fill_risk.

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 each mode: 'Call with NO args for a trending scan... pass `event` for the strongest per-event partition_check, or `topic` for a themed cross-event scan.' It also advises against trading when realizable_edge_pp ≤ 0 and references polymarket_fill_risk for custom sizing.

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 readOnly, openWorld, idempotent, non-destructive. The description adds extensive behavioral details: caching (1h KV keyed on knobs), response structure with by_segment and diagnostics, edge calculation including slippage and Kelly sizing, model family explanations, and Fed candidates exclusion. It goes well 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 well-structured with clear sections: model families, tradeable-edge knobs, response top-level. It front-loads the main purpose and then provides dense but valuable details. Every sentence adds value; it is as concise as possible given 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 complexity (9 parameters, three segments, diagnostics, caching, model details), the description is exceptionally complete. It explains the models (crypto_price, news_momentum, etc.), the edge calculation, filter logic, and response structure. No output schema exists, but the description details the response fields adequately.

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, but the tool description adds operational context for each parameter, e.g., 'Bump for very thin partitions; drop to 0 if you have a smarter fill model' for slippage_pp. It explains how knobs like min_liquidity and max_spread_pp affect tradeable-edge filtering, providing 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's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It specifies the verb (scan), resource (Polymarket markets), and product (edge opportunities). It distinguishes from siblings like polymarket_arbitrage by focusing on Pipeworx data disagreement.

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 use case: 'Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets.' It explains knobs like min_liquidity and max_spread_pp to filter tradeable edges. While it does not explicitly state when not to use this tool, the context is clear enough.

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, idempotentHint=true, and destructiveHint=false. The description adds valuable context: it reads from snapshots, computes trend and decay, notes that gaps occur when no scan happened, and clarifies that decay is based on daily closes, not intraday data.

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 detailed but well-organized: it starts with a concise summary, then explains the output format in a structured way (tracked[], expired[], snapshot_dates[]). While not extremely concise, every sentence contributes 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 lacking an output schema, the description thoroughly explains the response structure, including fields like first_seen, trend, decay_pp_per_day, and lifespan_days. It also covers limitations and data gaps, making the tool's behavior fully transparent.

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 parameter descriptions already clear. The description reiterates default and max for 'days' and confirms window options, but does not add significant new semantics beyond 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 the tool's purpose: providing edge persistence and decay telemetry from daily snapshots. It answers a specific question ('how long has this edge existed and is it shrinking?') and distinguishes itself from the sibling tool 'polymarket_edges' by focusing on time-series analysis rather than raw edge data.

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

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

The description gives strong usage context: it explains the importance of edge age for trading decisions and mentions limits like the 60-day TTL and snapshotting start. It does not explicitly state when NOT to use the tool, but the intended use case 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 (readOnlyHint, idempotentHint, etc.) are consistent. Description adds behavioral context: walks the ladder, returns verdict (clean|degraded|cannot_fill), explains risk of forced directional risk and partial fills. No contradiction.

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 well-structured with bold headings and clear separation of modes. Every sentence adds value, but the length could be slightly trimmed. Still, it remains focused and front-loaded with the core purpose.

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

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

Despite no output schema, the description enumerates all return fields for both modes (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict for single; theoretical_sum, realizable_sum, capture_ratio, profit_usd, per-leg fill, thin_legs, max_clean_notional_usd, forced_directional_risk for basket). Also covers prerequisites and risk warnings, making it fully informative for 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%. Description adds meaning beyond schema: explains how size_usd differs between modes (spend vs. target proceeds vs. settlement notional), side default auto for basket, and clamp range (10–1,000,000). Adds clarity not present in 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 a specific verb ('check') and resource ('realizable-vs-theoretical edge against live CLOB order-book depth'), clearly distinguishing two modes (single-market and basket). It differentiates from sibling tools like polymarket_arbitrage and polymarket_edges by stating it should be used before acting on those signals.

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: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500'. Provides rationale about thin books and partial basket risks, and implies when not to use (smaller trades).

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 declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds detailed behavioral context: two modes, response structure (leg-by-leg prices, matched spreads with top_spreads_pp), safety fields (compatibility_warning, temporal_alignment, skipped counters), and explains when spreads are meaningful. 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?

The description is dense and front-loaded with purpose. It uses clear sectioning (modes, response, safety fields) and every sentence adds value. Slightly verbose but necessary given tool complexity; structure could be improved with explicit bullet lists.

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, no output schema, and rich annotations, the description provides thorough coverage: response format, safety fields, edge cases (compatibility scenarios), and limitations (temporal misalignment). It is complete for an agent to understand invocation and interpretation.

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 all three parameters described. The description adds value by listing the 10 topic shortcuts, explaining how explicit parameters override topic mode, and providing examples. Baseline 3 is elevated because of meaningful elaboration 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 computes cross-venue spreads between Kalshi and Polymarket for the same resolving question. It distinguishes itself from sibling tools like polymarket_arbitrage by specifying cross-venue focus and providing two modes (topic shortcuts vs explicit pairings).

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?

Extensive guidance is provided: when to use topic mode vs explicit pairings, explanation of compatibility_warning scenarios (non-equivalent bet shapes, semantically unrelated events), and temporal alignment importance. It explicitly warns that pre-mapped topics often yield warnings and are not necessarily tradeable.

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, destructiveHint, and openWorldHint, covering the safety profile. The description adds no behavioral traits beyond 'single product', which is minimal but not contradictory. With annotations, a 3 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 extremely concise (two words), which is good for conciseness but at the cost of missing crucial information. It is not appropriately sized for the tool's context among many siblings.

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 complexity of sibling tools and the presence of an output schema, the description is incomplete. It does not differentiate from other product tools or explain what 'single product' means (e.g., details, price, or metadata). The context is insufficient for an 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?

The single parameter 'product_id' has no description, and schema description coverage is 0%. The description does not explain the parameter meaning, format, or provide examples beyond the schema's examples. It fails to add value over 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?

Description is 'Single product.' which restates the name without providing a verb or action. It implies the tool deals with a single product but doesn't specify if it retrieves, searches, or validates. Compared to siblings like 'products' (plural) it suggests a singular entity, but purpose is vague.

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 like 'products', 'product_book', or 'product_ticker'. There is no mention of context or exclusions, leaving the agent to guess.

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 readOnly, idempotent, non-destructive. The description adds that it is live, from a specific venue, and that levels control depth. This adds operational 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?

Two sentences, no filler, front-loaded with purpose. Every sentence provides value. 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 output schema exists, return format is covered. Description explains inputs, use cases, and venue. Missing default level behavior, but overall complete for a non-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?

With 0% schema coverage, description adds meaning: product_id is a crypto pair like 'BTC-USD', level controls depth (1-3). Could be more specific about level's exact effect, but sufficient for 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 returns a live order book with bids and asks for a crypto pair, specifically from Coinbase Exchange. It distinguishes from sibling tools like product_ticker and product_trades by focusing on depth data.

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

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

It explicitly lists use cases: spread analysis, liquidity assessment, market making. While it doesn't mention when not to use, the context of siblings implies alternatives. Slight gap in explicit 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds behavioral context by specifying the data type (OHLC candles), granularities, and exchange, 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 two sentences, front-loaded with the main purpose, and every word adds value. 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?

With an output schema, the description does not need to detail return values. However, it omits information about data range limits, maximum candles returned, or any rate limits. The examples in the schema partially fill gaps, but the description could be more complete for 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?

The input schema has 0% description coverage. The description mentions granularity options (1m, 5m, 15m, 1h, 6h, 1d) but does not explain the format for start/end parameters or that granularity must be in seconds. The schema's examples help, but the description could provide more parameter guidance.

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

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

The description clearly states it provides OHLC candles for a crypto pair on Coinbase Exchange, specifies granularity options, and notes usage for charting and backtesting. This differentiates it from sibling tools like product_book, product_ticker, and product_trades.

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 says 'Use for charting and backtesting on Coinbase-listed pairs', which indicates when to use it. However, it does not explicitly mention when not to use it or provide alternatives among siblings.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, indicating a safe, read-only operation. The description adds useful context about the returned data (base/quote currency, min order size, status, trading rules), enhancing transparency without contradiction.

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, well-structured sentence that front-loads the key information ('Coinbase Exchange — list all available trading pairs'). No wasted words; every piece of information is necessary 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 the simplicity of the tool (no parameters, clear annotations, and an output schema), the description is complete. It sufficiently explains what the tool does and what data it returns, leaving no gaps for the 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?

The input schema has zero parameters, so the description does not need to explain parameter semantics. Schema description coverage is 100%. The description does not add parameter info because none exist, which 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 it lists all available trading pairs (products) with specific attributes like base/quote currency, min order size, status, and trading rules. The verb 'list' and resource 'products' are specific, and it distinguishes from sibling tools like 'product' (singular) and specific data 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 does not explicitly state when to use this tool versus alternatives. While the sibling names imply that this tool is for getting the full list and others are for specific details, no explicit guidance is provided. Usage is implied but not directed.

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 cover safety and idempotency; description adds context: data source (Coinbase Exchange), time window (24-hour rolling), and specific fields. 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?

Two short sentences, no fluff, front-loaded with key info. Every sentence earns its place.

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 only one required param and output schema present, description adequately covers purpose, return fields, and usage context. Slight gap: doesn't clarify that return is a single object or if it contains all listed fields directly.

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?

Zero schema description coverage, so description must compensate. Only implies product_id is a crypto pair, but lacks format details (e.g., 'BTC-USD') or constraints.

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?

Clear purpose: retrieves 24-hour rolling stats for a crypto pair, listing specific fields. Distinguishes well from siblings like product_ticker or product_candles, though could more explicitly contrast.

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?

States 'Use for daily summary' which implies when to use, but no explicit alternatives or 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 declare readOnlyHint=true and idempotentHint=true, so the description adds value by specifying the data source (Coinbase Exchange) and the data fields included. No contradictory or additional behavioral traits are disclosed 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?

The description is two sentences, front-loaded with the venue and data fields, followed by a usage recommendation. Every word adds value, with no redundancy.

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

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

Given the tool's simplicity (one parameter, clear annotations, and an output schema), the description sufficiently covers what data is returned, where it comes from, and when to use it.

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 schema has no description for the single parameter 'product_id,' and the description does not explicitly define the format (e.g., BASE-QUOTE). However, it implies the parameter is a crypto pair by mentioning 'crypto pair' and 'Coinbase-listed pair.' This partially compensates for the missing 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?

The description clearly states the tool provides best bid/ask, last trade price, and volume for a crypto pair on Coinbase Exchange. This distinguishes it from sibling tools like product_book, product_candles, and product_stats, which serve different purposes.

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 current pricing on a Coinbase-listed pair,' giving clear context. While it does not explicitly state when not to use it, the context of sibling tools makes the usage intention 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 already declare readOnlyHint and idempotentHint, so the safety profile is clear. The description adds value by specifying return fields and pagination behavior, but does not mention rate limits or auth requirements.

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 key information: what it returns and how to paginate. 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 the presence of output schema for return fields and annotations for safety, the description covers the core functionality and pagination. It lacks explicit ordering details but is sufficient for an agent to use correctly.

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

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

Schema coverage is 0%, so the description must compensate. It explains product_id via example and mentions limit and before/after as pagination params, but does not define what 'before' and 'after' are (cursor IDs). Examples in schema provide some help but are not part of the 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 recent trade tape for a crypto pair, listing specific fields (trade ID, price, size, side, timestamp). It distinguishes from siblings like product_book and product_candles by focusing on trades.

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 getting recent trades with pagination support, but it does not explicitly compare with sibling tools or state when not to use this tool. The mention of limit and before/after provides contextual 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?

Adds scoping detail (anonymous IP, BYO key hash, account ID) and behavior for omitted key, which enriches the readOnly/idempotent annotations. 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 concise, front-loaded sentences with no wasted words. Each sentence adds critical 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 single optional parameter, no output schema, and rich annotations, the description fully covers purpose, usage, and behavior without 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% with a clear description for 'key'. The tool description reinforces the optional nature and listing behavior, adding examples 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 retrieves saved values or lists all keys, with explicit examples (ticker, address, notes) that distinguish it from sibling tools remember and forget.

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 (look up context) and how to list keys (omit key). Pairs with remember/forget, providing complete 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, openWorldHint, idempotentHint, and non-destructive behavior. The description adds context about return fields and the effect of mark_read (which flags events read, potentially altering subsequent calls). This additional detail compensates for no explicit statement about state changes; 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?

The description is concise (4 sentences) and well-structured: purpose, return fields, filtering and mark_read, polling and alternative access. 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?

With no output schema, the description covers return values (source, citation_uri, raw payload) and explains behavior of key parameters. It addresses polling and alternate access. Slight omission of error handling or empty result scenarios, but sufficient 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% (baseline 3). The description adds meaning beyond the schema by explaining the subscription type filter, that 'since' is an ISO timestamp, and the behavior of 'mark_read' and 'unread_only'. It also describes return fields, adding value for parameter semantics.

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: 'Pull fired events from your subscription feed.' It specifies what it returns (recent alerts with source, citation_uri, and raw payload) and is distinct from sibling tools like list_subscriptions.

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 guidance on filtering by type and since, explains the mark_read parameter effect, and notes that polling works and an alternative endpoint exists. However, it does not explicitly state when not to use this tool or differentiate it from all 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?

Beyond annotations (readOnly, idempotent, not destructive), the description discloses the fan-out to multiple sources, fallback strategy, date shorthand, and the USPTO soft-fail. This comprehensive behavioral context adds significant value.

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 packed with essential information. It uses examples and structured source enumeration without redundancy, earning its length.

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 specifies the return structure (changes[] grouped by source, total_changes, citation URIs) and failure modes. This fully compensates for the missing output schema, making the tool self-sufficient.

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, and the description adds further context: `type` is limited to 'company', `value` accepts ticker or CIK, `since` supports ISO and relative formats with suggested values. This enriches 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 a change feed (SEC filings, news, patents) for a company over a time window. It provides explicit query examples and distinguishes from the sibling `entity_profile` by noting when to use the latter instead.

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 gives explicit usage context: queries like 'What's new with X' and when to use `entity_profile`. It also details fallback logic (GDELT→GNews) and source behaviors.

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 idempotentHint=true and destructiveHint=false. The description adds behavioral details beyond annotations: key-value storage, persistence across sessions with auth, 24-hour memory for anonymous sessions, and pairing with recall/forget. 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?

The description is concise and front-loaded with purpose. Each sentence adds value, though it could be slightly more streamlined. Overall efficiently 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?

Given the tool's simplicity (2 params, no output schema, 100% schema coverage), the description is fairly complete. It covers purpose, usage, behavior, and pairing with siblings. Missing potential error details or limitations, but adequate 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 coverage is 100%, so baseline is 3. The description adds meaning by explaining key naming conventions ('subject_property') and that values can be any text, which is helpful 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 saves data for reuse across conversations/sessions, with specific examples (resolved ticker, target address). It distinguishes itself from siblings by explicitly pairing with recall and forget, making its unique role evident.

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 clear when-to-use guidance: 'when you discover something worth carrying forward.' It also mentions pairing with recall and forget. However, it does not explicitly state when not to use (e.g., for transient data), but 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?

Annotations already indicate read-only, open-world, idempotent, and non-destructive behavior. The description adds significant value by revealing that each call cascades through multiple internal endpoints, replacing 2-3 manual lookups, and providing citation URIs for each entity type. 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 well-structured with examples and a clear hierarchy. It is informative but slightly verbose; could be trimmed without losing value. However, it remains front-loaded with core 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?

Given the tool's complexity (two entity types with multiple input forms) and absence of output schema, the description fully covers what the tool does, what it returns, and how it behaves (cascading lookups). It is complete for an AI agent to correctly select and invoke the 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 description coverage is 100%, so the schema already documents both parameters. However, the description adds meaningful context: for 'company' it accepts ticker, CIK, or name and returns ticker+CIK+company_name+citation; for 'drug' it accepts brand/generic and returns RxCUI+ingredient+brand+citation. This enhances understanding beyond the schema.

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

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

The description clearly states the tool resolves user-spoken names to canonical/official identifiers. It provides specific examples of questions it answers ('ticker for...', 'CIK for...') and distinguishes itself as the first step when needing an ID. It lists supported types (company, drug) with detailed return values.

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 says 'Use FIRST whenever you have a name but need an ID', providing clear usage context. It gives examples of when to use it, but does not explicitly mention alternatives or when not to use it. Given sibling tools like 'entity_profile' or 'compare_entities', an exclusion could improve clarity.

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 annotations already declare the tool as read-only, open-world, idempotent, and non-destructive. The description adds behavioral context: it calls ai_visibility_check internally, requires 2-8 entities, treats the first as subject, and returns a ranked list with scores, confidence, and signal density. No contradictory information is present.

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 concise sentences plus a third in quotes. It is front-loaded with the core action, every sentence adds value, and there is no wasted text. The structure is clear 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?

Given the tool has 4 parameters, no output schema, and good annotations, the description adequately covers what the tool does, how it works internally, what it returns (ranked list with scores/confidence/signal density), and provides a use case. It explains the role of each parameter enough for an agent to correctly invoke the 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 adds meaningful context beyond the schema: it specifies that the first entity is treated as the 'subject' for narrative, explains the context parameter disambiguates common names, and indicates that 'models' includes 'workers-ai' (default) and 'anthropic' (with API key requirement). This enriches 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 compares AI visibility across multiple entities, probes each using ai_visibility_check, ranks by score, and surfaces most/least recognized. It distinguishes itself from siblings like ai_visibility_check (single entity) and compare_entities (general comparison) by specifying the verb 'compare' and the resource '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?

The description provides clear context: 'Useful for competitive AI-marketing audits' and gives an example question. However, it does not explicitly state when NOT to use this tool or offer alternative tools, though it implies that for single entity checks one should use ai_visibility_check.

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 fan-out to two external services, partial failure handling (sources_failed), and bundlephobia's first-time latency of 5-30s. Extends beyond annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false) without contradiction.

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 front-loaded with the core purpose and efficiently packs detailed behavioral notes. Slightly verbose but every sentence adds value; still quite concise given the information density.

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?

Returns summary block, per-advisory detail, links, alternative versions, and handles partial failures. No output schema, but description fully covers expected output fields and edge cases (e.g., bundlephobia timeout). Complete for a read-only, idempotent 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 clear descriptions for both parameters. Description adds value by stating version defaults to latest, scoped packages accepted, and explains the dependency between version and latest check, complementing 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?

Explicitly describes a composite check for npm packages covering license, advisories, version history, bundle size, and tree-shaking. Unambiguous verb 'scan_dependency' and resource 'npm package'. No sibling tool overlaps with this scope.

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?

Directly states when to use: when agent asks about safety, popularity, size, or cost of adding a package. Also clarifies NPM-only in v1 and that other ecosystems fall under deps.dev:version directly, providing clear usage boundaries.

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, open-world. The description adds valuable details: embedding model (BGE-base-en), windowing (500-char overlapping), cap (200K chars with truncation and flag), and return fields (character offsets, similarity scores). No contradiction.

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 with no wasted words. Core purpose in first sentence, followed by usage, pairing, and technical details. Each sentence serves a 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?

Given complexity, the description covers purpose, usage, behavior, parameters, limits, and pairing. No gaps identified.

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 all parameters (100% coverage). Description enhances by providing concrete query examples, restating limits with context, and explaining the return structure (passages, offsets, scores) though no output schema exists. The technical details (embedding model, window size) add meaning not in 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 defines the tool as semantic search inside a fetched record, with examples (SEC 10-K body, article) and specific outputs (top-N passages with offsets and scores). It distinguishes itself from siblings by mentioning the pair with ask_pipeworx_grounded.

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 the record is too big to cram into the prompt') and provides a direct alternative (ask_pipeworx_grounded). Also explains the complementary workflow with ask_pipeworx_grounded.

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 thoroughly discloses behavioral traits not in annotations: subscription creation, type-specific behaviors, delivery channel details, webhook signing, and auto-disable after 10 failures. No contradiction with annotations (readOnlyHint=false, idempotentHint=true, etc.).

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 dense and informative but structured as a single paragraph. While it contains all necessary information, it could be more readable with bullet points or clearer separation of concerns (types, delivery, constraints).

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 (multiple types, nested objects, delivery channels, no output schema), the description is remarkably complete. It covers input parameters, behavior, side effects, constraints, and return value, leaving no major 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?

With 100% schema coverage, the description adds significant value by providing concrete examples for each type, delivery channel options, phone verification requirement, and webhook secret handling. This goes well 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's purpose: creating a proactive monitoring subscription to a live-data event stream and returning the subscription ID. It distinguishes itself from sibling tools like list_subscriptions and unsubscribe.

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 the tool, including requirements (Pipeworx OAuth account), supported types, delivery channels, and limitations (SMS cap, webhook auto-disable). It lacks explicit when-not-to-use guidance but covers context well.

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 readOnlyHint and destructiveHint false, so the description adds moderate value by describing the return structure (category-bucketed examples, live catalog) and that it can be called with no arguments or a topic. 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?

The description is lengthy but front-loaded with common user queries and packed with useful information. While every sentence earns its place, 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?

No output schema exists, but the description adequately explains the return format (category-bucketed examples with tool+argument shapes) and covers the optional parameter. Complete enough for a discovery tool with good annotations.

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 one optional parameter. The description adds meaning by listing example topic values and explaining the effect of omitting it, improving upon the schema's minimal 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's purpose: returning category-bucketed example questions with tool+argument shapes, serving as the onboarding entry point. It distinguishes itself from sibling tools like ask_pipeworx and discover_tools by 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 advises use 'first when you do not yet know what Pipeworx can do for you'. Mentions optional topic parameter for focus. Lacks explicit when-not or alternative tools, but context provides enough clarity.

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, idempotentHint=true, and destructiveHint=false. The description adds no additional behavioral context, merely restating the tool's function.

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 (just 'Server time.'), front-loading the key purpose. However, a brief additional sentence could improve utility without harming conciseness.

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, existing annotations, output schema present), the description is mostly complete. Could specify format or timezone, but not essential.

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, so schema coverage is 100%. The description adds context that the tool returns time, which is sufficient for this zero-parameter tool.

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

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

The description 'Server time.' clearly indicates the tool returns the server's current time, distinguishing it from siblings like 'currency' or 'product' which serve different purposes.

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

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

No explicit guidance on when to use, but given no other time tool among siblings, usage is straightforward. The context is clear enough for an AI to understand when to invoke it.

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

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

Annotations indicate non-readonly, non-destructive, idempotent. Description adds ownership enforcement and soft-deletion details, aligning with annotations and providing extra value.

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 core action, followed by constraints. 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 single parameter, no output schema, and rich annotations, description fully covers tool behavior, constraints, and side effects.

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 with description for 'id'. Description adds 'by id' but no additional semantics needed. Baseline score 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 it cancels a subscription by id, with a specific verb and resource. It distinguishes from sibling tools like 'subscribe' and 'list_subscriptions'.

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 usage constraints: ownership enforcement and soft-deletion behavior. Does not explicitly list alternatives, but the simple context makes usage 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 already provide read-only, idempotent, and non-destructive hints. The description adds valuable behavioral context: it returns a verdict with five possible values, a structured form, actual value with citation, and percent delta. It also explains that it replaces multiple sequential calls. 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 and well-structured: it starts with trigger phrases, states the purpose, specifies scope and version, and lists outputs. Every sentence contributes valuable information without redundancy. It is front-loaded with the most important usage cues.

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 complete context: what the tool does, when to use it, what claims it supports, what outputs it returns, and how it replaces other calls. No additional information is needed for an agent to select and invoke 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?

The schema has 100% coverage with a single 'claim' parameter described as a natural-language factual claim with an example. The description enhances this by specifying the type of claims supported (company-financial) and the underlying sources (SEC EDGAR + XBRL). This 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 explicitly states the tool's purpose: verifying natural-language claims about company finances against authoritative sources. It provides concrete trigger phrases ('Is it true that...', 'fact check', etc.) and distinguishes itself from siblings by noting it replaces 4-6 sequential calls. The verb+resource is clear.

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 states when to use ('whenever the agent needs to check whether something a user said is factually correct') and gives trigger phrases. It also specifies the scope (company-financial claims for public US companies) and version limitations. However, it does not explicitly mention when not to use it or mention alternatives, which prevents a perfect score.

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