Scryfall

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds value by explaining probing multiple models, scoring method, return structure (per-model and combined view), and cost implications for Anthropic (BYO key). 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 a paragraph of three sentences, front-loaded with the main purpose. Every sentence adds essential information without waste, covering purpose, models, cost, return format, and use cases.

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

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

Given the tool has 4 parameters and no output schema, the description adequately covers the main aspects: return format (score, confidence, signals, raw_response) and combined view. It could mention error handling or rate limits but is sufficiently complete for the use cases listed.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds meaning by explaining the 'entity' parameter as the thing to ask about, 'models' defaults, '_apiKey' triggers Anthropic probing with BYO key, and 'context' disambiguates. It goes beyond the schema by noting the free default model.

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

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

The description clearly states the tool probes LLMs for entity knowledge and scores visibility (0-100) per model. It specifies use cases (AI-marketing audits, pre-launch brand checks, competitive monitoring) and distinguishes from siblings like scan_competitor_ai_presence by being more general.

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

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

The description provides clear context on when to use the tool (audits, brand checks, monitoring) and mentions default vs. Anthropic model requirements. However, it does not explicitly state when not to use it or list alternatives among siblings.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint. The description adds value by explaining internal routing, verified sources, and citation URIs (pipeworx://). It does not contradict annotations and provides context about the tool's safety and behavior beyond the structured 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 key guidance ('PREFER OVER WEB SEARCH'), then enumerates use cases and alternatives in a structured manner. While slightly long, every sentence serves a purpose: listing source types, providing examples, and differentiating siblings. No waste.

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

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

Given the tool's complexity (routing to thousands of tools) and the absence of an output schema, the description covers purpose, usage context, input examples, and output format (structured answer with citations). It mentions speed and tier compatibility, providing sufficient context for an agent to select and invoke the tool.

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

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

Input schema has 100% coverage with descriptions for each parameter, but the description adds synonyms (q, text, etc.) and provides examples (e.g., 'Apple's revenue in 2024'). This clarifies the expected input format and reduces ambiguity for the agent.

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 answers factual questions by routing to 5,008 verified sources across 1,318 domains, distinguishing it from siblings like ask_pipeworx_grounded and deep_research. It specifies the type of data (SEC filings, FDA, etc.) and explicitly differentiates when to use each sibling.

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: 'PREFER OVER WEB SEARCH', 'START HERE for most questions', and directs to ask_pipeworx_grounded for hallucination-resistant answers and deep_research for broad queries. It lists specific query types and even warns against using it for breaking news, which is already covered.

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

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

Annotations already cover safety (readOnly, openWorld, idempotent, non-destructive). Description adds value by explaining the beta status, the nature of routing improvements (source-preference ranking), and that it is a full working router with no fallback. 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?

Description is a single paragraph that is informative but slightly verbose. Every sentence contributes meaning, but could be more concise. Front-loaded with key identification.

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

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

Given no output schema, description mentions 'same response shape' but does not specify the return format. However, it adequately covers the tool's purpose, usage context, and behavioral traits. For a beta tool with sibling reference, it is reasonably complete.

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

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

Schema coverage is 100%, so the schema already documents all parameters (question and its aliases). Description does not add new semantic information beyond what the schema provides, only repeating alias info. 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?

Description clearly identifies it as a beta version of ask_pipeworx, a universal router with identical toolset, and distinguishes from the stable router by mentioning candidate routing improvements and source-preference ranking. The verb 'ask' and resource 'Pipeworx' are specific.

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 it exactly like ask_pipeworx when you want the newest routing', providing clear context for when to use. It contrasts with the stable router and mentions comparison for merges, but does not explicitly exclude use cases or list alternatives beyond the stable version.

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?

Describes in detail the internal routing, data fetching, extraction process, and return fields including answer, evidence, confidence, source, and various refusal reasons. This goes well beyond annotations which only indicate readOnly and idempotent.

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

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

The description is detailed but front-loaded with the core purpose and key differentiators. While every sentence adds value, it could be slightly more concise without losing critical information.

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

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

Given no output schema, the description fully explains the return format, including success fields and explicit refusal reasons, enabling the agent to handle responses correctly. It also covers cost implications and edge cases.

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

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

Schema coverage is 100% with all parameters well-described as aliases for the question. The description adds no extra semantics beyond what the schema already 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 it is a hallucination-resistant answer mode for high-stakes reads, specifying that it extracts answers only from tool results. It distinguishes itself from sibling 'ask_pipeworx' by emphasizing groundedness and explicit refusal reasons.

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 (high-stakes where answers will be quoted/cited/acted on, e.g., financial, legal, medical) and when not to (prefer ask_pipeworx for casual lookups). 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?

The description extensively covers behavioral traits: resolver contract, parent event extraction, news fallback, safety short-circuits, wide-spread warnings, and resolution-rule risk. Annotations already declare read-only, idempotent, non-destructive; the description adds crucial edge-case 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 long (~2000 chars) but well-structured with capital-letter section headers. It contains redundant detail (e.g., listing classifiers and examples). Could be more concise without losing clarity.

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 fully explains the return shape (result.market, result.analysis, result.evidence), match confidence, parent events, news behavior, safety guards, and cancellation rules. Covers all necessary context for this complex tool.

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

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

Schema covers all 3 parameters (100%). The description adds value by explaining the 'depth' default and rationale for 'include_raw' true/false, and reiterates 'market' input formats. This goes beyond schema but is not excessive.

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: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It specifies inputs (slug, URL, question text) and outputs (evidence packet + comparison). The tool is distinct from sibling polymarket tools.

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

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

The description explicitly states when to use: 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z".' It does not explicitly exclude other scenarios or name alternatives, but the context is clear.

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

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

Annotations already indicate read-only, non-destructive, idempotent behavior. The description adds valuable context: data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), handling of off-calendar fiscal years, sorting by primary metric, and return of citation URIs. No contradictions.

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

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

The description is concise (6 sentences), well-structured with example queries first, then usage preference, data details, and output. 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?

Without an output schema, the description mentions 'paired data + pipeworx:// citation URIs,' giving high-level output context. It covers data sources, sorting, and handling of fiscal years. A minor gap is the exact output structure, but sufficient for a query 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 descriptions for both parameters (type enum, values array). The description adds practical examples (tickers/CIKs for company, drug names) and explains the effect of each type, 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 defines the tool's purpose: side-by-side comparison of 2-5 companies or drugs. It uses specific verbs like 'compare', 'vs', 'rank', and explicitly states it replaces 8-15 sequential lookups, distinguishing it from single-entity tools like 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?

Explicitly states 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' Provides clear query examples and implies when not to use (single entity lookups). This gives strong guidance to the AI agent.

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

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

Annotations already indicate readOnly, openWorld, idempotent, non-destructive. The description adds rich behavioral detail: decomposes questions, routes to 5,008 tools in parallel, returns findings packet with evidence/confidence/source/citation/gaps, describes depth levels and hop iteration, time expectations (15-90s), and edge cases like empty gaps for non-structured topics. 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 long but well-structured with front-loaded key information (account requirement, alternative, core capability). Every sentence adds value, covering purpose, usage, behavior, edge cases, and outputs. A minor deduction for density that could be slightly more scannable, but overall earned.

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 2 parameters, no output schema, and existing annotations, the description is exceptionally complete. It describes what the tool returns (findings packet with fields: verbatim evidence, confidence, source, fetched_at, citation, gaps, contradictions, hop, citation_uri), explains depth behavior, handles edge cases (empty gaps, large record excerpting), and sets time expectations. No gaps remain.

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

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

Schema coverage is 100%, so baseline is 3. The description adds considerable value beyond the schema: explains the implications of each depth level (quick=3 facets, standard=5+gap recovery+contradictions, thorough=8+iterative chase+contradictions), and clarifies that broad multi-part questions are expected. However, the enum descriptions in the schema already cover base meanings, so the added value is contextual rather than foundational.

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

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

The description clearly identifies the tool's purpose: grounded multi-source research across structured data sources, not open-web search. It uses a specific verb ('research') and resource ('Pipeworx's 1318 STRUCTURED data sources'), and differentiates from siblings like ask_pipeworx and bet_research by emphasizing parallel decomposition and evidence citation.

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 use ('BREAKING or colloquial CURRENT-NEWS topics'). Points to alternative ask_pipeworx for single lookups and news, and mentions account requirements with fallback. Provides clear decision 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 readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds behavioral context by stating that results include 'full input schemas (with curated examples) — each result is ready to call directly, no second schema lookup needed.' This enriches transparency beyond annotations without contradiction.

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

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

The description is front-loaded with the core verb phrase 'Find tools by describing the data or task.' It then efficiently lists domain examples and explains the return format. Every sentence serves a purpose, and the structure is clear and concise.

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

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

Given no output schema, the description fully explains what is returned: names, descriptions, and full input schemas with examples. It states results are ready to call directly. For a discovery tool, this is complete and leaves no ambiguity.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining that the query parameter should be a 'Natural language description of what you want to do' and lists aliases. It also provides concrete examples in the schema schema examples, which 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's purpose: 'Find tools by describing the data or task.' It lists specific domains (SEC filings, financials, etc.) and explains it returns top-N relevant tools with schemas. It differentiates from siblings by positioning itself as the first call for tool discovery.

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

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

The description explicitly states when to use: 'when you need to browse, search, look up, or discover what tools exist for:' and provides domain examples. It also advises 'Call this FIRST when you have many tools and want to see the option set (not just one answer).' This provides clear context and 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 declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context: it is a parallel call, fans out across multiple sources, specifies return fields and limits (up to 5 filings), and notes patent soft-fail behavior. No contradictions with annotations.

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

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

The description is well-structured with front-loaded examples and clear behavioral guidelines. While it is verbose, every sentence adds value. It could be slightly more concise, but the structure supports quick understanding.

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 is complex with multiple data sources and no output schema. The description covers the main return fields (cik, filings, fundamentals, patents, news, LEI) with specifics like URIs and patent soft-fail. It provides sufficient context for an agent to understand what will be returned.

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 further meaning by providing examples, emphasizing that names are unsupported, and clarifying the use of ticker vs CIK. This 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?

The description clearly states the tool's purpose: providing a full cross-source profile for a US public company. It includes multiple example queries and explicitly distinguishes itself from sibling tools by stating to prefer over chaining single-pack lookups.

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

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

The description explicitly says when to use this tool (for holistic views) and when not to (for names, recommending resolve_entity instead). It provides guidance on input format (ticker or CIK) and emphasizes preference over 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 adds context beyond annotations (e.g., sensitive data clearing). Consistent with destructiveHint=true; 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?

Two sentences, no fluff. Front-loaded with core action, then usage guidance.

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

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

Simple tool with one parameter; description fully covers purpose, usage, and relationship to siblings.

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 parameter fully (100% coverage). Description adds no extra info beyond 'by key'.

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 action (delete) and resource (memory by key). Distinguishes from siblings like 'remember' and 'recall'.

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

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

Explicitly states when to use: stale context, task done, clear sensitive data. Mentions pairing with 'remember' and 'recall'.

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

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and no destructiveness. The description adds behavioral details: 'Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format', which aligns with and enriches the annotation hints without contradiction.

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

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

Three sentences cover the tool's function, method, and use cases. Each sentence is essential, front-loaded with the main purpose, and 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?

Given the tool's simplicity (2 parameters, no output schema), the description thoroughly explains what it does, how it works, and what the output looks like (a text blob in markdown format). It is complete 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% with descriptions for both parameters. The description adds minimal new information beyond the schema, such as 'key links' and the output format. While it provides context, it does not significantly deepen understanding of parameter meaning.

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 generates a production-ready llms.txt file for any URL, specifying the verb 'Generate' and the resource 'llms.txt file'. It further explains the purpose for AI crawlers and provides use cases that distinguish it from sibling tools like 'scan_competitor_ai_presence'.

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

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

The description lists specific use cases (getting a client's site indexed, drafting for own project, auditing a competitor), offering clear context on when to use. However, it does not explicitly mention when not to use or provide direct alternatives, slightly reducing clarity.

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

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

Annotations already declare readOnlyHint and idempotentHint. The description adds behavioral context beyond annotations by specifying it returns full card details including mana cost, oracle text, colors, prices, legalities, and image, and uses fuzzy matching. 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?

Extremely concise: two sentences that front-load the purpose and return contents. No unnecessary words.

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

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

Given the simplicity of the tool (2 params, no output schema, strong annotations), the description covers the core functionality and return details. Could mention handling of non-existent cards, but overall sufficient.

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

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

Input schemas for both parameters (name, set) have 100% description coverage. The description does not add further semantics beyond what the schema provides, but it does not need to. 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 looks up a single MTG card by name using fuzzy matching, which distinguishes it from sibling tools like search_cards and random_card. The verb-resource pair is specific and unambiguous.

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

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

The description implies when to use (single card lookup by name) but does not explicitly mention when not to use or provide alternatives. Sibling tools such as search_cards (for multiple results) and list_sets exist, but no guidance on selection.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds only that it lists specific fields, which is minimal additional behavioral context. 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?

Single sentence, front-loaded with 'List all Magic: The Gathering sets/expansions', 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?

Lists the return fields (codes, names, types, release dates, card counts) but does not mention ordering, pagination, or scope (all sets ever?). Minimal but adequate for a simple list tool with no parameters.

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

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

There are 0 parameters and schema coverage is 100%. Baseline for 0 params is 4. Description does not need to add parameter info.

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

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

The description states it lists MTG sets/expansions with specific fields (codes, names, types, release dates, card counts). The verb 'List' and resource are clear, and it distinguishes from sibling tools like 'list_subscriptions'.

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

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

No explicit when-to-use or when-not-to-use guidance. The tool is simple with no parameters, so implied usage is straightforward, but it could mention that it returns all sets without filtering.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint (false). Description adds value by detailing the returned fields and stating it lists active subscriptions, confirming non-destructive behavior without contradicting annotations.

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

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

Two sentences with no wasted words. First sentence states purpose and return fields; second provides usage guidance. Well front-loaded and efficient.

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

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

For a read-only list tool with one parameter and no output schema, description is complete: it covers what it does, what it returns, and when to use it. 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 has 100% coverage for the single parameter (include_inactive) with a good description. Description does not add new param info, so 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?

Description clearly states 'List the caller's active subscriptions' with a specific verb and resource, and lists exact return fields (id, type, params, etc.), distinguishing it from siblings 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 advises use for reviewing subscriptions before adding more or finding an id to cancel, providing clear context. No explicit exclusions or alternatives, but the guidance is actionable.

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

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

Discloses rate limit of 5 per identifier per day, free usage, and no impact on tool-call quota. Annotations (all false) are consistent with no destructive behavior. Missing details on success/failure responses, but acceptable for a simple feedback tool.

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

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

Concise yet informative; front-loaded with purpose and usage guidance. Each sentence adds value, though slightly lengthy. Could be marginally tighter without losing content.

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

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

Given the tool's simplicity (3 params, 100% schema coverage, no output schema), the description fully covers what the agent needs: purpose, when to use, how to format, and behavioral notes. No gaps identified.

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

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

Schema has 100% coverage with good field descriptions. The description adds value by explaining the meaning of each type, advising against pasting user prompts, and specifying the message format (plain text, max 2000 chars). This 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 sends feedback to the Pipeworx team, specifying categories (bug, feature, data_gap, praise). It uniquely distinguishes from sibling tools which are all unrelated to feedback.

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 (bug, missing feature, data gap, praise), provides formatting guidance (describe in terms of tools/packs, not user prompts), and mentions rate limits and quota. No alternative feedback tools exist among siblings.

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

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

Annotations already indicate read-only, idempotent, non-destructive. Description adds useful context: data from CF analytics-engine, no PII, caching behavior (5min-1h). 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?

Single paragraph with front-loaded purpose, bulleted use cases, and concise additional context. Every sentence earns its place; no fluff.

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

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

For a simple tool with one optional parameter and no output schema, the description covers purpose, use cases, data source, privacy, caching, and returns. Complete 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?

Only one parameter (window) with 100% schema coverage. Description adds semantic guidance on how windows affect results (hot vs steady-state), beyond the enum values.

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

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

The description clearly states it returns top tools, packs, and call volume for trending data. It distinguishes from siblings like 'ask_pipeworx' and 'discover_tools' by focusing on aggregated call volume.

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

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

Three explicit use cases are provided: discovering hot data sources, confirming canonical tools, and aligning use cases. Window choice guidance is given, but no explicit when-not or alternatives are mentioned.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds extensive behavioral context: monotonicity violations, partition-sum checks, semantic anchor (Jaccard similarity), partition filter (placeholder slugs), and fill check against CLOB depth. 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 long but well-structured with paragraphs and clear sections (modes, semantic anchor, partition filter, fill check). It is front-loaded with the main purpose. While every sentence earns its place given complexity, slight trimming could improve conciseness.

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

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

No output schema exists, so the description must explain return values. It does: 'Response: opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context)... fill check...' Covers all aspects thoroughly, including edge cases (skip_low_similarity, placeholders_filtered).

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, but the tool description adds significant meaning beyond schema: explains each mode's behavior, valid inputs (event slugs, topic seed questions), and even details like 'Full Polymarket URLs also accepted.' This is well beyond baseline.

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

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

The description states the tool's purpose clearly: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It distinguishes between the three modes (no args, event, topic) and explains what each does, leaving no ambiguity about the tool's function.

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

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

Explicit usage guidance is provided: 'Call with NO args for a trending_scan... pass `event` for... pass `topic` for...' It also includes when not to use (e.g., 'do not trade it' if realizable edge ≤0) and references sibling tools for custom sizing (polymarket_fill_risk).

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

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

Annotations indicate the tool is read-only, idempotent, and non-destructive. The description adds extensive behavioral details: caching strategy (1h KV keyed on knobs), response structure with diagnostics, filter rules, model families, and edge computation formulas. 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 well-structured: begins with purpose, then details model families, response fields, tradeable-edge knobs, and response structure. Every sentence provides value, and the technical depth is necessary for the tool's complexity. No wasted words.

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

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

Despite no output schema, the description thoroughly explains the response structure (by_segment segments, each opportunity fields, diagnostics, fed section) and caching behavior. It covers all aspects a user or agent needs to understand how to interpret results, making it complete for the tool's complexity.

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

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

Schema covers all 9 parameters with descriptions (100% coverage). The tool description enhances this by providing practical usage guidance, e.g., setting min_liquidity to 5000 to avoid thin books, or explaining that min_kelly doesn't filter partition arbs and min_partition_leg_kelly should be used instead. This adds significant real-world value.

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

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

Description clearly states the tool scans Polymarket markets for opportunities where Pipeworx data disagrees with market price, explicitly targeting the 'what should I bet on today' use case. This distinguishes it from sibling tools like polymarket_arbitrage which likely focuses on pure cross-market arbitrage.

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

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

The description provides clear context: built for daily betting discovery, automates scanning hundreds of markets. It implies when to use (discovering edges) but does not explicitly list when not to use or directly compare to all sibling tools, though the purpose is evident.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds significant behavioral context: explains output structure (tracked, expired, snapshot_dates), limits (60-day TTL, decay from daily closes), and that missing snapshots indicate no scan on that day. 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 front-loaded with the main purpose. It is not excessively verbose; each sentence adds information. However, it could be slightly more structured (e.g., bullets for response fields) to improve readability.

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

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

Given no output schema, the description fully covers what the tool returns: tracked edges with time series, trend, and decay; expired edges with lifespan; snapshot dates. It also mentions limitations (60-day TTL, data gaps). Adequate for an agent to use correctly.

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

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

Schema coverage is 100%; both parameters are described. The description adds minor context like 'snapshot family' for window, but mostly repeats schema info. Baseline score of 3 is appropriate as the schema already carries the load.

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: 'Edge persistence and decay telemetry built from daily polymarket_edges snapshots.' It answers a specific question about edge duration and decay, distinguishing it from sibling tool 'polymarket_edges' which likely provides current edges, not historical trends.

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

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

It provides context on when to use: for distinguishing between fresh and old edges, implying historical analysis. It does not explicitly exclude alternatives or state when not to use, but the context is clear enough for an agent.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint; description adds behavioral context: walks ladder, returns specific fields, warns about partial fills and forced directional risk. Mentions live CLOB data source, making 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?

Well-structured with capitalized section headings, front-loaded purpose. Every sentence is informative, but the list of return fields could be more concise. Still, it earns its length given 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, description thoroughly covers inputs, outputs, and edge cases. Explains both modes, default behaviors, return fields, and risk warnings. Leaves no obvious gaps for an AI agent to select and use correctly.

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

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

Schema coverage is 100% and schema descriptions are detailed. Description adds value by explaining mode-specific interpretations (e.g., size_usd as settlement notional in basket mode) and the auto side logic, enriching but not radically extending schema content.

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 checks realizable vs theoretical edge against live order-book depth. Distinguishes two modes (single-market and basket) and explicitly positions itself as a prerequisite to polymarket_arbitrage and polymarket_edges, differentiating from sibling tools.

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

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

Explicitly states when to use: before acting on arb/edge signals, especially above $500. Provides rationale (theoretical overround not capturable, partial fills create directional risk). Also specifies required parameters for each mode and defaults.

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

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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds rich behavioral context: two modes, response structure (leg-by-leg prices, top_spreads_pp, compatibility_warning), temporal alignment, and skipped counters. It explains exactly what happens in failure cases (matched_pairs:0 with different conditions). 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 somewhat long but well-structured and front-loaded. Each sentence adds value, covering modes, response, safety fields, and caveats. Minor verbosity keeps it from a 5, but it is still efficient relative to 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?

Despite the lack of an output schema, the description thoroughly documents the response structure and edge cases. It covers compatibility warnings, temporal alignment, skipped types, and the meaning of top_spreads_pp. Given the tool's complexity, the description is fully complete.

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

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

Schema coverage is 100%, so parameters are already documented. The description adds meaning by explaining the interaction between topic and explicit parameters, listing all valid topic values, and giving examples. It clarifies that explicit parameters override the topic-mapped side and provides context on 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 states 'Cross-venue spread between Kalshi and Polymarket for the same resolving question' which is a specific verb+resource. It distinguishes from siblings by detailing two modes (topic and explicit) and highlighting that it compares only same outcomes, unlike other tools that might do arbitrage on different venues.

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

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

The description explicitly explains when to use each mode, notes that most pre-mapped topics currently return compatibility_warning, and provides guidance on interpreting safety fields. It tells the agent when spreads are meaningful and when they are not, fulfilling the 'when-not' criterion.

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 include idempotentHint=true, but the tool returns a random card, which is not idempotent (same query can yield different results). The description does not clarify this or add any behavioral context beyond the bare minimum. This is a contradiction.

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

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

The description is a single concise sentence that front-loads the purpose. However, it lacks structural elements like bullet points or sections that could improve scannability.

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

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

Given there is no output schema, the description should explain the return format (e.g., a card object with properties). It does not, leaving the agent guessing what data to expect. Sibling tools like 'get_card' likely provide more detail, but this description is incomplete.

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

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

The input schema has 100% coverage, describing the query parameter as optional. The description adds examples of valid queries (e.g., 'is:commander'), providing practical context that the schema alone does not.

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

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

The description clearly states the verb 'Get' and resource 'random MTG card', with optional filtering. It distinguishes from sibling tools like 'get_card' (specific card) and 'search_cards' (multiple cards) by emphasizing randomness.

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 optional filtering but does not explicitly state when to use this tool versus alternatives (e.g., 'get_card' for a known card, 'search_cards' for specific searches). No when-not or alternative guidance is given.

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

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds useful context about scoping to an identifier and relationships with sibling tools, providing value beyond annotations.

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

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

Two sentences, tightly written with no fluff. Purpose is front-loaded, and every sentence adds value, including usage guidance and scope.

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 no output schema, the description explains both use cases (single key retrieval and listing) and scoping. Lacks format details, but is complete enough for the complexity.

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

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

With 100% schema coverage, the description adds practical context: omitting the key lists all keys, and gives examples of what keys might contain (ticker, address, notes), enhancing meaning beyond the schema.

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

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

The description clearly states the tool retrieves a saved value or lists all keys, distinguishing it from sibling tools like 'remember' and 'forget'. It specifies both operations and the resource.

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

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

The description explicitly states when to use the tool ('look up context the agent stored earlier') and mentions pairing with 'remember' and 'forget'. However, it does not explicitly state when not to use it or provide direct 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?

The description discloses return structure (source, citation_uri, raw payload) and behavioral traits like mark_read marking events read, and polling being fine. Annotations already provide safety hints, but the description adds value by detailing side effects.

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

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

The description is five sentences, front-loaded with the main action, and covers key points efficiently 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 the five parameters and no output schema, the description explains return structure and mark_read behavior, and mentions an alternative access method. It is mostly complete, though details on limit, unread_only, and pagination are implicit.

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 parameters are well-documented. The description rephrases some parameter uses (type, since, mark_read) but does not add significant meaning beyond the 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?

The description clearly states the tool pulls fired events from the subscription feed, specifying the verb 'pull' and the resource 'alerts/events'. It distinguishes from siblings like subscribe and list_subscriptions by focusing on reading recent alerts.

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 guidance on filtering by type and since, using mark_read to manage read state, and mentions polling suitability. It also notes an alternative access method via URL, but does not explicitly state when not to use this tool.

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, idempotentHint), the description discloses fan-out behavior, fallback from GDELT to GNews on rate limits/5xx, USPTO soft-fail until reactivated, and return structure with grouped changes 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 functional and front-loaded with examples, but it is somewhat lengthy. Every sentence is valuable, but could be slightly more compact without losing information.

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

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

Given the complexity (multiple sources, fallback, soft-fail, no output schema), the description is highly complete. It explains the return structure and behavior, and the output schema is not needed due to clear textual description.

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 meaning: explains 'since' accepts ISO date or relative shorthand with examples ('30d', '1m'), and 'value' can be ticker or CIK. This goes beyond the schema descriptions.

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

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

The description explicitly states the tool's purpose: a change feed for a company covering recent activity from multiple sources (SEC, GDELT/GNews, USPTO) in one parallel call. It uses clear examples like 'What's new with X' and distinguishes from 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?

Provides explicit guidance on when to use (e.g., 'latest on Y', 'updates on Acme') and when not to use ('Use entity_profile instead when you want the static profile'). This helps the agent select the correct tool.

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

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

The description adds behavioral context beyond annotations, such as scoping by identifier, persistence differences between authenticated (persistent) and anonymous (24 hours) sessions, and pairing instructions with recall/forget. 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 with four sentences. It front-loads the main purpose and provides useful details 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?

For a simple storage tool with two required string parameters and no output schema, the description is complete. It covers purpose, usage, storage semantics, and persistence 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 descriptions for both key and value parameters. The description adds context about key-value pair storage and examples but does not significantly enhance meaning beyond the schema.

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

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

The description clearly states the tool's purpose: 'Save data the agent will need to reuse later.' It specifies the resource (data for reuse across conversations/sessions) and distinguishes it from sibling tools like recall and forget.

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

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

The description provides clear guidance on when to use the tool: 'Use when you discover something worth carrying forward... so you don't have to look it up again.' It also mentions pairing with recall and forget, though it doesn't explicitly list when not to use it.

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

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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds value by explaining internal cascading through several lookup endpoints and specifying output details (citation URIs). 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 and well-structured. It starts with user-facing examples, then provides usage guidance, and details supported types with output specifics. Every sentence is informative and 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 the tool's simplicity (2 parameters, rich annotations, no output schema), the description is complete. It explains return values for both entity types, including citation URIs, which compensates for the lack of output schema.

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

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

Schema coverage is 100%, so parameter names and types are clear. The description adds examples and clarifies acceptable input formats (e.g., ticker, CIK, name for company; brand or generic for drug), which enhances understanding beyond the schema.

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

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

The description clearly states the tool resolves names to canonical identifiers, with examples and supported types. It distinguishes itself from sibling tools by focusing on identifier 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?

The description explicitly says 'Use FIRST whenever you have a name but need an ID,' providing clear guidance. It also notes that using resolve_entity replaces 2-3 manual lookups, implying efficiency. However, it doesn't explicitly say when NOT to use it or name 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?

Annotations already declare read-only, idempotent, non-destructive behavior. The description adds valuable context by explaining the tool internally probes each entity with ai_visibility_check, ranks by score, and returns a ranked list. No contradiction with annotations.

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

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

The description is concise (three sentences) and front-loaded with the main purpose. Every sentence provides essential information 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 the tool has no output schema and 4 parameters, the description covers what the tool does, how it works (calling ai_visibility_check), its input constraints, and the output format. It is complete for the complexity level.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds extra meaning by noting the first entity is treated as the 'subject' for narrative and that context disambiguates common names, going beyond schema.

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

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

The description clearly states the tool compares AI visibility across multiple entities side-by-side, using specific verbs like 'compare', 'probes', 'ranks', and 'surfaces'. It distinguishes from siblings like ai_visibility_check by explicitly noting it handles multiple entities.

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

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

The description provides a clear use case ('competitive AI-marketing audits') and an example question, giving context for when to use. However, it does not explicitly mention when not to use or contrast with alternatives like compare_entities.

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

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

Discloses partial failure behavior, timing for bundlephobia measurements (5-30s on first call), and that sources_failed will list timeouts. Annotations already declare readOnly, openWorld, idempotent, non-destructive; description adds valuable operational 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 a single paragraph that packs a lot of information efficiently. It is front-loaded with the main purpose and quickly covers usage, return values, and limitations. Slightly long but every sentence is justified.

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 details the return format: summary block with specific fields, per-advisory details, links, and alternative versions. It covers the ecosystem limitation, partial failures, and timing. Highly complete for the tool's complexity.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by noting scoped packages accepted and default version behavior. This elevates it slightly above baseline.

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

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

The description clearly states it is a composite check for npm packages combining deps.dev and bundlephobia data. It uses specific verbs ('scan', 'check', 'fans out') and distinguishes from siblings by focusing on npm packages only.

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 ('is X safe / popular / small') and excludes other ecosystems (PyPI, Maven, etc.), directing them to deps.dev:version directly. 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 already indicate readOnly and idempotent behavior. The description adds that it uses Scryfall syntax and returns specific fields, but it does not disclose potential limits, pagination, or error scenarios. Given annotation coverage, the added context is adequate but not extensive.

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

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

Two concise sentences: first states purpose with examples, second lists return fields. No superfluous content; every sentence adds value.

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

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

Despite no output schema, the description specifies return fields (names, types, oracle text, etc.) which is sufficient for a search tool. It does not mention result count limits or pagination, but overall is fairly 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 coverage is 100% and includes parameter descriptions. The description adds value by providing concrete query examples (e.g., 'c:red type:dragon'), which clarify the query parameter's usage 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 searches MTG cards using Scryfall query syntax and lists return fields. However, it does not explicitly differentiate from sibling tools like get_card (for single card lookup) or random_card, so it loses some clarity for distinguishing 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?

No guidance on when to use this tool versus alternatives. It does not mention that get_card is for specific card details or that random_card is for random draws, nor does it specify when not to use this search.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds specific technical details: embedding model (BGE-base-en), windowing (500-char overlapping), similarity metric (cosine), and a 200K char cap with truncation flagging. 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 5 sentences, front-loaded with purpose, then usage, benefits, pairing, and technical details. Every sentence adds value without redundancy or 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?

Despite lacking an output schema, the description explains the return format (passages with offsets and scores), the cap and truncation behavior, and the pairing with ask_pipeworx_grounded. The agent has enough information to use the tool effectively.

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

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

Schema coverage is 100% with each parameter described. The description adds minor context (e.g., 'pass the text you already pulled' for text, query examples) but does not significantly enhance understanding beyond the schema.

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

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

The description clearly states it performs semantic search inside a fetched record, returning top-N passages with offsets and similarity scores. It distinguishes itself from sibling tools like ask_pipeworx_grounded by specifying it is for searching inside a record rather than generating grounded responses.

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 the record is too big to cram into the prompt' and pairs with ask_pipeworx_grounded. It provides clear context for when to use the tool but does not explicitly mention when not to use it or list alternatives beyond the paired tool.

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 extensively discloses behavioral traits beyond annotations, including OAuth requirement, persistence model, rate limits on SMS (10/day), webhook signing and auto-disable after failures, and verified phone requirement. Annotations correctly mark idempotent (idempotentHint: true) and non-destructive, with 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 well-structured with a clear flow from core purpose to requirements, types, and delivery options. Each sentence adds value, though it is relatively long. It front-loads the main action and benefits from bullet-style formatting in the original (not shown here) but remains efficient.

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

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

Given the complexity (3 params, nested objects, no output schema), the description covers most aspects but lacks details on idempotency behavior (e.g., what happens if same subscription already exists), error scenarios, or return format beyond the mention of returning a subscription id. Minor gaps prevent a higher score.

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

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

With 100% schema coverage, baseline is 3. The description adds significant value by explaining type-specific params (e.g., sec_8k items codes, polymarket_edge topic, fred_series series_id) and delivery constraints (e.g., phone verification, webhook signing), going well beyond the schema's property descriptions.

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

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

The description clearly states the tool's purpose with a specific verb ('Create') and resource ('proactive monitoring subscription'), and distinguishes it from sibling tools like list_subscriptions and unsubscribe by focusing on creation of new subscriptions.

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

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

The description provides clear context on when to use (requires Pipeworx OAuth account) and when not (anonymous/BYO cannot persist), and explains supported subscription types with examples. However, it does not explicitly mention alternatives for listing or unsubscribing, though the sibling context makes it implicit.

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 as false. The description adds behavioral context by stating the tool returns example questions with exact tool + argument shape drawn from the live catalog, which goes beyond the annotations. No contradictions.

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

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

The description is well-structured, starting with example user phrasings, then explaining the tool's function, output, and usage. It is information-dense without unnecessary words. Slightly long but earns its length.

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

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

Given the tool has one optional parameter, no output schema, and clear annotations, the description is complete. It covers purpose, usage, parameter semantics, and behavioral context. No gaps remain.

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

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

The input schema has 100% coverage with a single 'topic' parameter described. The description adds value by listing example topics (e.g., 'finance', 'pharma') and explaining that omitting topic gives a cross-category spread, which enhances understanding beyond the schema.

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

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

The description clearly states it is an onboarding entry point, explains what it returns (category-bucketed example questions with tool usage), and distinguishes itself from siblings by specifying 'Use this FIRST when you do not yet know what Pipeworx can do for you.'

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

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

The description explicitly states when to use: when the user is unfamiliar with Pipeworx or wants to learn how to call meta-tools. It also explains that calling with no arguments gives the full spread, while passing a topic focuses the results. This provides clear usage context, though it does not explicitly state when not to use.

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

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

Annotations indicate non-readOnly, non-destructive, idempotent. The description adds context: deactivation (not deletion), ownership enforcement, and that historical events remain available. This supplements the annotation hints well.

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

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

Two concise sentences with no wasted words. Key information is front-loaded: action, constraints, side effects, and relation to other tools.

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, no output schema, and moderate complexity, the description covers purpose, constraints (ownership), behavior (deactivate not delete), and ties to 'recent_alerts' for historical context. It is complete.

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

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

The single parameter 'id' is fully described in the schema ('Subscription id (uuid) returned by subscribe'). The description does not add additional meaning, so baseline 3 applies with 100% schema coverage.

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

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

The description clearly states the action (Cancel a subscription by id) and resource (subscription). It distinguishes from sibling tools like 'subscribe' and 'list_subscriptions' by specifying deactivation instead of deletion, and implies the result's availability via 'recent_alerts'.

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 ownership enforcement ('you can only cancel your own subscriptions') and hints at alternative tool 'recent_alerts' for historical events. However, it does not explicitly state when to avoid using this tool or compare to siblings beyond the ownership note.

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=true, openWorldHint=true, etc. Description adds value by detailing the return structure (verdict, actual value with citation, reasoning) and the dual-path pipeline.

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?

Slightly long but every sentence earns its place with examples, path details, and return info. Front-loaded with trigger phrases.

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

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

Given no output schema, description fully explains return values. Parameters are well-documented. Context with siblings and annotations makes this complete.

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

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

Schema coverage is 100% so baseline 3. Description adds meaning for tolerance_pct: explains override for hallucination detection and default behavior. Adds value beyond schema.

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

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

Description starts with trigger phrases and clearly states it performs claim verification against authoritative sources. It distinguishes from siblings by noting it replaces 4-6 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?

Explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct.' Clarifies two paths for company financial vs other claims. No explicit when-not, but the context is clear.

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