Protein Atlas

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint. Description adds behavioral traits: calls LLMs, requires API key for Anthropic (with cost implication), returns per-model data with raw response. Does not mention rate limits or error handling.

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

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

Three well-structured sentences: purpose, details (default model and key requirement), and use cases. No wasted words. Information density high and front-loaded.

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

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

Despite no output schema, description specifies return format (per-model fields + combined view). Covers input, output, use cases, and cost implications. Adequate for moderate complexity with 4 parameters and clear 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% (all 4 parameters described in schema). Description adds meaning: explains default model, indicates _apiKey only needed for Anthropic, and clarifies that context helps disambiguate common names.

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

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

Description clearly states it probes LLMs for business visibility and scores it 0-100. Verb 'probe' and 'score' with specific resource 'business/brand/product/topic'. Differentiates from sibling 'scan_competitor_ai_presence' by being more generic and providing per-model scores.

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

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

Explicitly lists use cases (AI-marketing audits, pre-launch brand checks, competitive monitoring). Explains default model vs. Anthropic with key requirement. No explicit 'when not to use' or alternatives, but context is clear.

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

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

Adds significant context beyond annotations: routes to 4,819 tools across 1259 sources, returns structured answers with citation URIs, mentions speed and tier accessibility. 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?

Relatively long but well-structured, front-loaded with key instruction, and each sentence adds useful guidance or examples.

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?

Comprehensive: explains what the tool does, what it returns (structured answer with citations), and how it differs from siblings. No output schema, so description adequately covers return behavior.

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 parameters described as aliases for 'question'. The description adds value by clarifying the type of questions suitable and providing examples, elevating above 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 the tool routes questions to verified sources for authoritative structured data with citations. It distinguishes itself from web search and sibling tools like ask_pipeworx_grounded and deep_research.

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

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

Explicitly says 'PREFER OVER WEB SEARCH', provides when to use (factual questions) and when to step up to alternatives. Includes examples and a clear hierarchy.

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 provide readOnly/idempotent/destructive hints. The description adds substantial behavioral context: hallucination resistance, explicit refusals, extra LLM call, and return format details. 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 a single focused paragraph with front-loaded purpose. Every sentence adds value, though it is somewhat lengthy.

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?

Covered all necessary aspects: behavior, return format with explicit fields, refusal reasons, use cases, cost comparison, and distinction from sibling. No output schema but return structure is fully described.

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

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

Schema coverage is 100% with descriptions for each alias. The tool description does not add additional meaning beyond what the schema provides for parameters.

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 as a 'hallucination-resistant answer mode for high-stakes reads' and explains it extracts answers using only tool results. It distinguishes from sibling 'ask_pipeworx' by noting explicit refusals and extra cost.

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 (when answer will be quoted/cited/acted on and facts must not be invented) and when to prefer 'ask_pipeworx' for casual lookups.

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 read-only, idempotent, non-destructive. Description adds extensive behavioral context: market resolution, classification, fan-out, response shapes, resolver contract, parent event extraction, safety checks, spread warnings, cancellation risks. 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 long but tightly packed with value. Each section serves a purpose: usage, classifiers, fan-out examples, response shapes, resolver contract, safety. Could be slightly shorter but remains structured and front-loaded.

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

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

Given no output schema, the description covers return fields (result.market, result.analysis, result.evidence), resolver confidence, parent events, news fallbacks, and edge cases. Appears complete for an agent to invoke and interpret results.

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

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

Schema coverage is 100%, and description adds meaning: explains market input types (slug, URL, text), depth options (quick vs thorough with source counts), include_raw with size estimates. This goes beyond schema descriptions.

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

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

The description clearly states the tool researches a Polymarket bet by pulling Pipeworx data. It specifies input types (slug, URL, question text). This is a specific verb+resource, and it distinguishes from siblings by focusing on Polymarket betting research.

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

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

Explicitly recommends use cases: 'should I bet on X', 'what does the data say about Y', 'is there edge in Z'. Does not mention when not to use or alternatives, but context is clear enough for an agent to decide.

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, openWorldHint, idempotentHint) indicate safe, non-destructive behavior. The description adds substantial behavioral context: for company type, it explains data source (SEC EDGAR/XBRL), financial metrics pulled, and off-calendar handling; for drug type, it lists FAERS, FDA approvals, and trial counts. It also mentions sorting by primary metric and citation URIs. 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 somewhat lengthy but every sentence adds value—trigger phrases, type-specific details, sorting behavior, and citation mention. It front-loads with common query examples. Could be slightly tightened, but remains efficient for the complexity.

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

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

Given the tool's complexity (two entity types, multiple data sources, sorting, citations), the description is remarkably complete. No output schema exists, but the description covers return format (paired data + citation URIs) and data sources. It satisfies all contextual needs for an agent to 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?

Schema coverage is 100% with descriptions for both type and values. The description adds significant meaning: it explains that type can be 'company' or 'drug' with data source examples, for values it specifies tickers/CIKs for companies and drug names, with min/max constraints. It also explains result structure (sorted by primary metric) and output format, going well beyond the schema definitions.

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 performs side-by-side comparisons of 2-5 companies or drugs, using common query phrases like 'compare X and Y' and 'head to head', and explicitly distinguishes from sequential lookups. It specifies the verb (compare) and resource (entities) with a 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?

The description explicitly advises to 'ALWAYS PREFER over sequential single-pack lookups' and provides contextual trigger phrases. It does not explicitly list when not to use or mention alternative tools, but the sibling list includes entity_profile and search_within, which could serve as alternatives. The guidance is strong but lacks exclusion criteria.

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

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

Annotations already declare readOnly, openWorld, idempotent, non-destructive. The description adds crucial details: account requirement, free vs paid, parallelism, return format (findings packet with verbatim evidence, confidence, source, citations, gaps[]), 15-60s latency, and guarantee not to invent. 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?

Every sentence adds value, with key caveats front-loaded. The description is longer than typical but information-dense and well-structured. Could be slightly more concise, but the level of detail is justified by tool 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 no output schema, the description fully explains return format (findings packet with specific fields). Covers prerequisites (account, paid plan), limitations (not for breaking news), latency, and alternatives. No gaps remain for an agent to understand usage.

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 for both parameters. The description adds extra context: depth enum meanings (quick=3, standard=5, thorough=8, paid), and clarifies question should be natural language and broad/multi-part. This adds value beyond schema, so above 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 the tool is for grounded multi-source research across 1259 structured data sources, distinguishing it from open-web search and single-lookup alternatives. It uses specific verbs like 'decomposes' and 'routes in parallel', and the name 'deep_research' aligns well with the purpose.

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

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

Explicitly states when to use (broad/multi-part questions over structured data) and when not to (single lookup, breaking news). Provides alternatives: ask_pipeworx for single lookups or if not signed in, and mentions paid plan requirement for 'thorough' depth.

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 state readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds significant behavioral context beyond annotations: 'Returns the top-N most relevant tools with names, descriptions, and full input schemas (with curated examples) — each result is ready to call directly, no second schema lookup needed.' This explains output format and readiness, which is not covered by 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 (~100 words) and well-structured: it front-loads the purpose and usage, then lists specific domains. Every sentence adds value, with no fluff or repetition.

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

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

No output schema is present, but the description explains what is returned (top-N tools with names, descriptions, full schemas, and examples). It also specifies the limit parameter and aliases. Given the tool's complexity and the richness of structured fields, the description is complete for an agent to understand 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?

Schema coverage is 100%, so the baseline is 3. The description mentions the 'query' parameter is a natural language description and lists aliases, which adds minimal meaning beyond the schema's own description. The schema already provides examples and detailed descriptions for each parameter.

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

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

The description clearly states the tool's purpose: 'Find tools by describing the data or task.' It lists specific domains (SEC filings, financials, etc.) and emphasizes that it returns tool names, descriptions, and schemas. This distinguishes it from sibling tools, which are specific to particular tasks or data sources.

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

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

The description provides explicit when-to-use guidance: 'Use when you need to browse, search, look up, or discover what tools exist for...' and 'Call this FIRST when you have many tools available and want to see the option set.' It implies not to use when you already know the tool or need a single answer, but it does not list explicit 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, openWorldHint, idempotentHint. Description adds rich behavioral context: fans out across SEC EDGAR, XBRL, USPTO, news, GLEIF; notes USPTO PatentsView API sunset May 2025 with soft-fall; explains fallback from GDELT to GNews; details return fields including CIK, filings with URIs, fundamentals sorted, patents, news, LEI. 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 detailed and well-structured, with key information front-loaded. Slightly verbose but every sentence adds value—examples, constraints, data sources, and return fields are all covered efficiently.

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 comprehensively lists return fields (CIK, filings, fundamentals, patents, news, LEI) and explains source behaviors and limitations (soft-fail, name restriction). For a complex multi-source tool, this is complete enough for an agent to understand 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?

Schema coverage is 100%, but description adds value by clarifying that type is only 'company' currently, value must be ticker or zero-padded CIK, and names are not supported. Examples provided. Adds context beyond schema definitions.

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 profiles a US public company across multiple sources, provides example queries, and distinguishes from chaining single-pack lookups. The verb 'profile' and resource 'entity' are specific, and it defines the holistic 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?

Explicitly states 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view' and notes that names are not supported, directing to use resolve_entity first. This provides clear when-to-use and alternative 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 provide destructiveHint=true and idempotentHint=true. The description adds 'delete' and 'memory' but does not detail behavior for missing keys or error conditions. With annotations covering the destructive nature, a score of 3 is appropriate.

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

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

Three sentences, front-loaded with the action, then usage, then pairing. 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?

Low complexity tool with 1 parameter and good annotations. The description covers purpose and usage well, though it omits handling of missing keys and return value. Still sufficiently 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?

Input schema has 100% coverage with one parameter 'key' and description 'Memory key to delete'. The description adds 'by key' but no additional meaning. Baseline 3 for high coverage.

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

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

The description states 'Delete a previously stored memory by key', which is a specific verb-resource pair. It clearly distinguishes from siblings 'remember' (store) and 'recall' (retrieve).

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 when context is stale, the task is done, or you want to clear sensitive data' and pairs with 'remember' and 'recall'. This provides clear context and 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 declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds behavioral context by detailing the process (fetches page, extracts title/description/key links) and output format (single text blob). 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: two effective sentences plus a bullet-like list of use cases. It front-loads the main purpose and avoids any fluff. Every sentence adds value.

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

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

Given no output schema, the description sufficiently explains the output format and usage. Annotations cover safety. Both parameters are documented. The tool's complexity is low, and the description covers all necessary aspects.

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. The description reinforces the default/max for max_links but adds minimal new meaning beyond the schema. Baseline of 3 is appropriate.

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

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

The description clearly states the tool's action ('generate a production-ready llms.txt file') and the resource ('any URL'). It distinguishes from siblings like 'scan_competitor_ai_presence' by focusing on generating the file itself rather than scanning or checking.

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 use cases (client site, own project, auditing competitor) which helps the agent judge applicability. However, it lacks explicit 'when not to use' or alternative tool recommendations, but the context is still 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 readOnly, openWorld, idempotent, non-destructive. Description adds value by stating 'keyless' (no API key needed) and describing the returned fields (trimmed profile). 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?

Two sentences only, both packed with information. First sentence gives purpose with example and field list. Second sentence adds prerequisite and keyless info. Front-loaded and 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?

No output schema, but description explains what is returned (gene, description, protein class, etc.). Mentions trimmed nature and keyless. For a simple retrieval tool with one parameter, this is adequate and fairly 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% with a good description. Description adds an example value and clarifies the format (ENSG...). Adds 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?

Clearly states the action (get), resource (Human Protein Atlas profile), scope (trimmed, one protein), and key input (Ensembl gene id). Provides an example and lists fields returned. Distinguishes from sibling search_genes.

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

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

Explicitly says to use search_genes to find the Ensembl id before using this tool. Does not explicitly state when not to use it, but the prerequisite is clear. No alternatives mentioned for getting protein info.

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

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

Annotations already declare readOnlyHint and idempotentHint. Description adds that it returns specific fields and defaults to active subscriptions, which is consistent. 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?

Two sentences: first states purpose and returns, second gives usage guidance. No redundant information, 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?

Given no output schema, the description specifies return fields. Single parameter fully covered by schema. Annotations cover safety. Description is complete for an agent to understand and use 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% for the single parameter. The description does not add additional meaning beyond what the schema provides, so baseline score of 3 is appropriate.

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

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

The description clearly states 'List the caller's active subscriptions' with a specific verb and resource. It lists the return fields and distinguishes from sibling tools like subscribe/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?

Explicitly states when to use: to review monitoring before adding more subscriptions or to find an id to cancel. Provides clear context and exclusion criteria.

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 provide no behavioral hints, but description adds critical behavior: rate-limited to 5/identifier/day, free, no quota impact, and describes how feedback is processed (daily digests, roadmap influence). 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?

Single paragraph with purpose first, then guidelines, then behavior. Every sentence adds value; no wasteful repetition.

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

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

For a feedback tool with 3 params and no output schema, description covers all necessary aspects: when to use, what to include, how it's processed, and constraints. Agent can invoke correctly without additional context.

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

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

Schema coverage is 100%, so baseline is 3. Description adds extra guidance: message should be specific, use tool/pack terminology, and describes type enum values in more detail than 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 the tool sends feedback to Pipeworx team, lists exact feedback types (bug, feature, etc.), and distinguishes itself from sibling tools by being a communication channel for issues/praise.

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

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

Explicitly tells when to use each feedback type, provides a negative instruction (don't paste end-user prompt), and mentions rate limits and cost/free nature.

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

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

Annotations already provide readOnlyHint, idempotentHint, openWorldHint, and destructiveHint. The description adds value by disclosing the data source ('derived from CF analytics-engine'), stating no PII, and noting caching behavior ('Cached 5min-1h depending on window'). 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?

Two short paragraphs; first sentence immediately states the main function. Every sentence adds value without redundancy. No filler.

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 return values (top tools, top packs, total call volume) and caching. Annotations cover safety and idempotency. The single optional parameter is fully documented. Complete for this simple 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 enum descriptions that explain the effect of each window (shorter for trending, longer for steady-state). The description reinforces this. The baseline is 3 due to high coverage, but the description adds extra context about window 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 uses a specific verb and resource: 'Returns the top tools, top packs, and total call volume'. It clearly distinguishes from sibling tools like 'discover_tools' by focusing on trending data derived from analytics.

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?

Description explicitly lists three use cases (discovering hot data sources, confirming canonical choices, aligning use cases). However, it does not explicitly state when not to use the tool or mention alternatives, though the context is clear.

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

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

Annotations already show readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so safety is transparent. Description adds behavioral depth: explains semantic anchor (Jaccard similarity), partition filter, fill check (theoretical vs realizable edge), and that skipped pairs are surfaced. No contradiction, and adds valuable 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 verbose but well-structured, starting with the main purpose, then detailing each mode. Every sentence adds necessary detail for a complex tool. Slightly long, but justified by the tool's sophistication.

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 response structure: 'opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}. FILL CHECK...' Covers all aspects needed for an agent to use the tool correctly.

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

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

Input schema covers both parameters with 100% description coverage. Description adds rich semantics: explains the two distinct modes (event and topic), what triggers them, and that no args does a trending scan. Provides concrete examples (slugs, URLs, seed questions). Adds meaning beyond schema.

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

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

Clearly states 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' The verb (find), resource (arbitrage opportunities on Polymarket), and method are explicit. Distinguishes from siblings like polymarket_edges and polymarket_fill_risk by focusing on arbitrage detection.

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 with NO args for a trending_scan... pass event for... partition_check, or topic for a themed cross-event scan.' Recommends 'event (recommended for a specific market)' and points to sibling 'For custom sizing use polymarket_fill_risk.' Provides clear when-to-use and 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?

Description discloses extensive behavioral details beyond annotations: model families, edge calculation, response structure, caching (1h KV-level), diagnostics, Fed note, and parameter interactions. All consistent with readOnlyHint and idempotentHint.

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

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

Description is lengthy but well-structured with sections. Front-loaded with purpose then details. Every sentence adds value, but could be trimmed slightly for agent efficiency. Still effective.

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

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

Given no output schema, the description thoroughly covers return structure (by_segment, diagnostics, Fed candidates), parameter effects, and caching behavior. Complete for an agent to invoke correctly without additional context.

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

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

Schema coverage is 100%, so baseline is 3. Description adds extra meaning by explaining how knobs like min_partition_leg_kelly and max_spread_pp affect filtering, which is beyond 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?

Clearly states it scans Polymarket markets for opportunities where Pipeworx data disagrees with market price. Specifies target use case 'what should I bet on today' and distinguishes from siblings like polymarket_arbitrage by focusing on Pipeworx data divergence.

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 when to use (betting advice) and how to tune with tradeable-edge knobs, but does not explicitly exclude use for other purposes or contrast with sibling tools. Still clear enough for an agent to determine applicability.

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 goes beyond by detailing the response structure (tracked[], expired[], snapshot_dates[]), explaining trend and decay_pp_per_day computation, and clarifying data sources and limitations. 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 detailed and well-structured, with logical sections: purpose, answer, parameter hints, response format, and limits. While somewhat lengthy, every sentence adds valuable information for an AI agent. Minor redundancy could be trimmed, but overall effective.

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

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

The tool has no output schema, so the description must fully explain return values. It provides a thorough breakdown of tracked, expired, and snapshot_dates fields, including edge_pp_net time-series, trend, decay, lifespan_days, and snapshot gaps. Limitations are also covered. Complete for its 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 description coverage is 100%, so parameters are documented. The description adds context about days as lookback and window as snapshot family, but does not significantly extend beyond the schema. It mentions defaults and clamps, but these are already in the schema description. 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: providing edge persistence and decay telemetry from daily snapshots. It asks the question 'how long has this edge existed and is it shrinking?' and distinguishes from sibling tools like polymarket_edges by focusing on historical trends rather than raw current edges.

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

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

The description implicitly guides usage by contrasting fresh vs. old edges, indicating when to use the tool. It mentions limits like 60-day snapshot TTL and daily close data. However, it does not explicitly state when not to use or name alternative tools for other scenarios, so it lacks full exclusion 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 signal read-only and idempotent behavior. The description adds rich behavioral details: walking the order book ladder, returning specific fields (slippage_pp, max_fillable_usd, verdict), explaining partial basket fill risks ('convert an arb into an unhedged directional position'), and describing forced_directional_risk. 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 dense but well-structured with capitalized mode labels and clear return field lists. Every sentence adds value, though the length is justified by the tool's complexity. It front-loads the core purpose and requirements.

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 comprehensively details all return fields for both modes, including edge cases (thin_legs, max_clean_notional_usd, forced_directional_risk). It covers usage warnings, parameter defaults, and the tool's role within the sibling toolset. 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 description coverage is 100%, so baseline is 3. The description repeats parameter defaults and modes but does not add new semantic information beyond what the schema already provides. It helpfully explains default modes (auto for basket) but does not go deeper.

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: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It details two distinct modes (single-market and basket), lists return fields, and explicitly references sibling tools (polymarket_arbitrage, polymarket_edges) to differentiate usage.

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: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It also warns about basket fill risks and thin books, and specifies the requirement for either market or event parameter. While it doesn't list all when-not-to-use scenarios, it effectively contextualizes usage.

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

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

The description adds substantial context beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false) by explaining bet shape equivalence, temporal alignment, compatibility warnings, and skipped types. It honestly discusses limitations, making the tool's behavior fully transparent.

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

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

The description is verbose but well-structured, front-loading the core purpose and using clear sections for modes, response, and safety fields. Some redundancy could be trimmed, but each sentence adds value.

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

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

The description adequately explains inputs, behavior, and outputs, including response structure, compatibility warnings, temporal alignment, and counters. Despite no output schema, an agent can fully understand what the tool returns and how to interpret 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?

With 100% schema description coverage, the description still adds meaning by explaining the two modes and how parameters interact (e.g., topic auto-fetches, explicit overrides). Examples in the schema further clarify usage.

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

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

The description clearly states it computes the cross-venue spread between Kalshi and Polymarket for the same resolving question, with specific verb ('compute' implied) and resource ('spread'). It distinguishes from sibling tools like polymarket_arbitrage by focusing on cross-venue 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?

The description explicitly outlines two modes (topic shortcuts and explicit pairing) and warns that most pre-mapped topics return compatibility warnings, indicating when not to use. However, it does not explicitly name alternative sibling tools for single-venue analysis, though it is implied.

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 destructiveHint=false, so the description does not need to repeat that. It adds useful context: behavior when key is omitted (list all keys), scoping to identifier, and pairing with remember/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?

Four sentences, no wasted words. Front-loaded with core action, then purpose, then scoping and pairing. Efficient and well-organized.

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

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

For a simple retrieval tool with one optional parameter, rich annotations, and no output schema, the description covers all necessary aspects: when to use, behavior with/without key, scoping, and relations to other tools.

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

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

Schema coverage is 100% with a description for the 'key' property. The description reinforces the behavior of omitting the key and provides examples of typical key values (ticker, address, notes), adding meaning beyond the schema alone.

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

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

Clearly states the tool retrieves a saved value or lists all keys. Specifies verb 'retrieve'/'list' and resource 'memory'. Differentiates from siblings remember and forget by explaining pairing. Provides concrete examples of use cases.

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

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

Describes when to use: to look up previously stored context without re-deriving. Specifies scoping to identifier. Implicitly suggests alternatives by mentioning remember and forget siblings, but does not explicitly state when not to use or exclude other 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?

The description states that setting mark_read=true flags events as read, causing a state change. This contradicts the readOnlyHint annotation which indicates no state modification. Contradiction detected.

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 three sentences, front-loaded with the core purpose, no redundant information. Every sentence adds value.

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

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

The description explains key behaviors (filtering, mark_read side effect) and alternative access. However, it lacks a full specification of the return format beyond mentioning three fields, which would be helpful given no output schema.

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

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

With 100% schema description coverage, the baseline is 3. The description adds valuable context: examples for type (e.g., 'sec_8k'), clarification that since is an ISO timestamp, and the behavioral effect of mark_read. This justifies a 4.

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

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

The description clearly states it pulls recent alerts from a subscription feed, specifies return fields and filtering options. The tool name and context distinguish it from siblings like list_subscriptions, 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?

The description mentions polling works and provides an alternative URL for scripts/dashboards, implying usage context. However, it does not explicitly guide when to use this tool versus sibling tools like list_subscriptions.

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, destructiveHint, idempotentHint, and openWorldHint. The description adds valuable context about the underlying data sources (SEC EDGAR, GDELT→GNews fallback, USPTO) and soft-fail behavior, exceeding what annotations provide.

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 front-loaded with usage examples and is well-structured. Every sentence adds value, though it is slightly verbose for a highly experienced audience.

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 the tool (multiple data sources, fallback logic, parameter flexibility), the description covers all essential aspects: fan-out, sources, parameters, return structure (changes grouped by source, total_changes, citation URIs). Even without an output schema, the return shape is described.

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

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

Schema coverage is 100%, but the description adds crucial details: 'since' accepts ISO dates or relative shorthand with examples, and 'value' can be ticker or CIK. This goes beyond the 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 explicitly states the tool's purpose with concrete examples: 'What's new with X', 'latest on Y', etc. It clearly defines it as a change feed for a company in a recent time window and distinguishes it from the sibling tool entity_profile.

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

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

The description provides clear usage patterns, including example queries and when to use this tool over entity_profile. It explains the fan-out logic across multiple data sources.

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 idempotentHint=true and destructiveHint=false. The description adds critical behavioral context: scope by identifier, persistent vs. anonymous session retention (24 hours), and pairing semantics. 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?

Three sentences front-load the core purpose, then progressively add usage, scoping, and pairing details. Every sentence serves a purpose; no redundant information.

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

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

For a simple 2-parameter tool with no output schema, the description covers purpose, data persistence, authentication nuance, and tool interdependencies. No gaps remain for agent decision-making.

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

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

Schema description coverage is 100%, providing clear parameter explanations with examples. The description adds value by framing key-value as 'scoped by your identifier' and emphasizing reusability, but the schema already handles format details adequately.

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

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

The description uses specific verbs ('save data', 'reuse later') and explicitly lists example payloads (resolved ticker, target address, user preference). It clearly distinguishes from sibling tools recall and forget by mentioning them as complementary 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?

Explicitly states when to use ('when you discover something worth carrying forward'), provides context (across conversation/sessions), and directs pairing with recall/forget. No ambiguity about its role.

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 no destructive behavior. The description adds that each call cascades through several endpoints internally, and details what each type returns (ticker, CIK, RxCUI, citations). This enriches the transparency 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 a single paragraph that is well-organized and front-loaded with examples. It is slightly lengthy but each sentence adds necessary context. Minor redundancy could be trimmed, but overall it is effective.

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

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

Given the tool has only 2 parameters, full schema coverage, safety annotations, and no output schema, the description covers all necessary aspects: use cases, supported types, return values, disambiguation, and replacement of multiple lookups. The agent has sufficient information to use the tool correctly.

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

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

Schema coverage is 100% with basic descriptions. The description greatly expands on both parameters: for 'type' it explains supported entities and their return contents; for 'value' it provides input examples (ticker, CIK, names) and mentions auto-disambiguation for companies.

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 starts with concrete examples like 'What's the ticker for...' and clearly states the tool resolves names to canonical IDs. It distinguishes itself from siblings by focusing on ID lookup and explicitly recommends using it first when an ID is needed.

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 FIRST whenever you have a name but need an ID.' It also mentions that the tool replaces multiple manual lookups. However, it does not explicitly state when not to use it or suggest alternatives for unsupported entity types, though 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 declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds behavioral context: it probes each entity with ai_visibility_check, ranks by score, and surfaces most/least recognized. It also describes the return format (ranked list with score, confidence, signal density). 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?

Three sentences, front-loaded with main action ('Compare AI visibility across multiple entities side-by-side'). 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?

Given no output schema, the description compensates by explaining return values (ranked list with score, confidence, signal density). It covers usage, examples, and behavioral context comprehensively for a moderate-complexity 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 every parameter is described in the schema. The description adds meaning: 'Probes each entity with ai_visibility_check' for entities, 'Passed to api.anthropic.com per probe' for _apiKey, 'Disambiguates common names' for context, and 'Omit for just workers-ai' for models. This significantly aids 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 side-by-side, probes each with ai_visibility_check, ranks by score, and surfaces most/least recognized. It distinguishes from siblings like ai_visibility_check (single entity) and compare_entities (generic 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?

The description explicitly says it is useful for competitive AI-marketing audits and provides an example quote. However, it does not explicitly state when not to use or alternatives beyond the sibling context.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds valuable context: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30 seconds, and lists exact return fields.

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 front-loaded with the core purpose but includes a detailed list of returned fields which, while necessary, makes it somewhat lengthy. Still concise for the complexity.

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

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

With no output schema, the description fully explains return values (summary block, advisories, links, alternatives) and handles edge cases like timeouts. Complete for a composite 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% and the description adds extra meaning: it clarifies scoped packages are accepted and that version defaults to latest when omitted, going beyond the schema.

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

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

The description clearly states it is a composite check for npm packages combining deps.dev and bundlephobia. It specifies the verb 'scan' and resource 'dependency', and distinguishes itself from a diverse set of sibling tools by focusing on this specific 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?

Explicitly defines when to use: when an agent asks about safety, popularity, size, or cost. Also notes NPM-only in v1 and points to alternatives for other ecosystems.

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. The description adds 'Keyless' indicating no authentication needed, but does not disclose other behaviors like pagination or rate limits, which are still useful 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?

The description is two sentences, front-loaded with the core purpose, and includes only essential information without fluff.

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

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

Given low complexity and full schema coverage, the description adequately covers the return fields (Ensembl id, synonyms, description) and the keyless nature, though pagination behavior is not explicitly mentioned.

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%, both parameters have descriptions. The description restates query as 'gene symbol or keyword', adding no new semantic detail beyond the schema.

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

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

The description clearly states it searches the Human Protein Atlas by gene symbol or keyword, and specifies the returned fields including Ensembl gene id needed by sibling tools get_protein and top_tissues, distinguishing it from them.

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 context by mentioning that the Ensembl id is required by get_protein and top_tissues, but does not explicitly state when not to use or list alternative 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?

Goes beyond annotations by detailing output (passages with offsets and similarity scores), embedding model (BGE-base-en), chunking strategy (500-char windows), and 200K char limit with truncation flag. Annotations only hint at safety and idempotency.

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 concentrated sentences plus technical detail. Front-loaded with core purpose. 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?

Covers when to use, what to expect (passages with offsets), technical limitations (200K chars, truncation), and relationship with sibling tool. No output schema, but description compensates well.

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

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

Schema coverage is 100%, but description adds meaning: explains 'text' as already fetched, 'query' as natural-language with examples, and 'limit' as max passages. Adds value beyond parameter names and types.

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 'Semantic search INSIDE a fetched record' with specific examples (SEC 10-K, article). It distinguishes from siblings like ask_pipeworx_grounded by explaining the fetch-then-search workflow.

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

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

Explicitly says 'Use when the record is too big to cram into the prompt' and pairs with ask_pipeworx_grounded. Provides clear context but doesn't explicitly exclude other use cases.

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

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

Annotations declare idempotentHint=true, but the description implies each call creates a new subscription, which is somewhat ambiguous. However, the description reveals important behaviors: SMS has 10/day cap, phone must be verified first, webhook auto-disabled after 10 failures, and webhook signing secret returned once. These details add 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?

The description is dense but well-structured: purpose first, then prerequisites, then type list with examples, then delivery details. Every sentence adds value, though the type-specific examples are somewhat lengthy. Still efficient and easily scannable.

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

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

Covers core aspects: creation, types, parameters, delivery, constraints. Missing details on the returned subscription object beyond id, but the description is sufficient for an agent to use the tool. Given the complexity (nested objects, multiple enums), it is adequately 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%, yet the description enriches each parameter with concrete examples, constraints (e.g., 'sponsor or condition required' for clinical_trial), and meanings of enum values (e.g., items codes for sec_8k). This helps an agent correctly compose the parameters.

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

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

Clearly states 'Create a proactive monitoring subscription to a live-data event stream. Returns the new subscription id.' The verb 'Create' and resource 'subscription' are specific, and it distinguishes from siblings like list_subscriptions and unsubscribe. Also details supported types and delivery channels, leaving no ambiguity.

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 prerequisites ('Requires a Pipeworx OAuth account') and examples for each subscription type. While it doesn't explicitly say when not to use, the context of sibling tools and the mention of delivery channels imply usage boundaries. Adequate guidance for an agent to decide.

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 destructiveHint=false, so the safety profile is clear. The description adds behavioral context: it returns example questions with tool+argument shapes, and explains how to call (no args for full spread, topic for focus).

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 (about 5 sentences), front-loaded with purpose, includes examples, and ends with usage guidance. No redundant or unnecessary information.

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

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

Given no output schema, the description explains the return type (category-bucketed example questions) and parameter usage. The annotations are rich. The tool is simple, and the description covers all needed context for an agent to use it correctly.

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

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

Schema coverage is 100% with the topic parameter described. The description adds examples ('finance', 'pharma', 'betting') and explains the effect of omitting vs providing topic, which goes 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 is an onboarding entry point that returns category-bucketed example questions with tool call shapes. It specifies verb 'returns' and resource 'example questions', and distinguishes from siblings like 'discover_tools' or 'ask_pipeworx'.

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

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

Explicitly says 'Use this FIRST when you do not yet know what Pipeworx can do' and mentions optional topic focus. While it doesn't list exact when-not-to-use scenarios, the context is clear and it references alternative meta-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 and no destruction; description adds 'keyless' (no API key) which is useful additional context. 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?

Two concise sentences, no wasted words. Purpose is front-loaded, making it quick to parse.

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

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

For a simple read-only tool with rich annotations, the description is complete. It explains input requirements, ordering, and access (keyless). No output schema needed for such a list.

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 both parameters with descriptions (100% coverage). Description adds context like 'highest first' but does not significantly extend beyond schema. Baseline 3 applies.

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

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

Clearly states the verb 'list', resource 'top-expressing human tissues by RNA expression (nTPM)', and scope 'for one Ensembl gene id'. Distinguishes from sibling tools like search_genes by directing users to it for ID lookup.

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 context: when to use (need top tissues for a gene) and prerequisite (use search_genes to find Ensembl id). Does not explicitly state when not to use, but clarity 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?

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description reveals that the row is deactivated not deleted, and that historical events remain available via recent_alerts. This adds valuable behavioral context and has 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?

Two concise sentences that front-load the core action and follow with key behavioral details. No unnecessary words; every sentence adds value.

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

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

For a simple tool with one parameter, the description covers the action, ownership constraint, deactivation behavior, and links to a related tool (recent_alerts). It is complete given the schema and annotations richness.

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 the id parameter described. The description adds context that the id is returned by subscribe, which aids in understanding its origin beyond the schema's 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 action (cancel) and the resource (subscription by id). It distinguishes itself from sibling tools like 'subscribe' and 'list_subscriptions' by mentioning ownership enforcement and soft deactivation.

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

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

The description explicitly mentions ownership enforcement as a condition for use, providing clear context on when the tool is appropriate. It does not explicitly mention alternatives or when not to use it, but the sibling list provides implicit cues.

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 goes beyond annotations by detailing the output structure (verdict types, structured form, actual value with citation, percent delta) and explaining its efficiency gains over multiple calls. Annotations already indicate safety, and the description adds rich behavioral context 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 front-loaded with the core purpose, uses bullet-like phrasing for clarity, and every sentence adds necessary information. It balances detail with readability.

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

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

Given the lack of an output schema, the description adequately explains the return values and behavior. It also notes the domain limitation, ensuring the agent understands scope.

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 of the 'claim' parameter. The tool description adds value by providing example claim formats, enhancing 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's purpose: natural-language claim verification against authoritative sources, specifically for company-financial claims. It gives concrete examples and distinguishes itself from potential alternatives by specifying the domain and replacing multiple sequential calls.

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

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

The description explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct.' It also limits the scope to company-financial claims, providing clear guidance on appropriate usage. However, it does not explicitly mention when not to use or provide alternatives.

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