Altos

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

Annotations already confirm readOnly, openWorld, idempotent, and non-destructive traits. The description adds value by clarifying that the default model (Workers AI Llama-3.3-70b) is free while Anthropic calls require a BYO key with direct payment. It also outlines the per-model return structure (score, confidence, signals, raw_response). No contradictions with annotations.

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

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

Three sentences front-load the core purpose and immediately cover models, API key, output, and use cases. Every sentence serves a distinct purpose 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 fully explains the return format. All parameters are described in the schema and enriched by the description. The tool's complexity (4 params, 1 required) is adequately addressed, and the context (use cases, cost implication) is sufficient for an agent to 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%, so the baseline is 3. The description improves understanding by explaining the default model for the 'models' parameter, tying '_apiKey' to Anthropic usage, and clarifying that 'context' helps disambiguate entities. This adds meaningful context 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 specifies a clear verb ('probe') and resource ('LLMs') with a measurable outcome ('score visibility 0-100 per model'). It distinctively covers business/brand/product/topic visibility audits, differentiating from sibling 'scan_competitor_ai_presence' which likely focuses on competitors. The default model and output format are stated.

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 use cases ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and provides guidance on when to supply an API key for Anthropic probing. However, it does not explicitly state when not to use the tool or mention alternative tools for similar tasks.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the tool is known to be safe and read-only. The description adds return field details (address, price, etc.) but does not disclose behavioral nuances like the date parameter being restricted to Fridays, which is only in the schema.

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

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

The description is two sentences, front-loaded with the core purpose and return fields. It includes a concrete example and has 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?

While the description covers basic purpose and return fields, it omits important details like the date constraint (must be Friday) and the region code format. With a tool of moderate complexity and existing output schema, the description provides adequate but not thorough context.

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

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

Schema coverage is 100%, but the description's example ('Denver, CO') is misleading as region expects a code like 'ca_los-angeles'. The description adds little semantic value beyond the schema and includes an inaccurate example.

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 'Search', the resource 'active property listings', and the scope 'in a region (e.g., Denver, CO)'. It distinguishes from sibling tools like altos_new_listings and altos_pending_sales by focusing on active listings.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, limitations, or when not to use it. Sibling tool names suggest differentiation but the description itself lacks explicit usage context.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint all true, and destructiveHint false, indicating a safe, read-only, idempotent operation. The description adds that it returns trends for specific metrics, which is consistent but not extra behavioral context. It does not disclose any additional traits such as rate limits, data freshness, or pagination.

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

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

The description is extremely concise: two sentences with no redundancy. The first sentence states the action and provides an example, the second lists the return values. Every word serves a purpose.

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

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

Given the tool has 3 well-documented parameters, rich annotations, and an output schema, the description is adequate. It explains the core functionality and typical usage. It could be slightly more complete by explicitly mentioning the output schema structure or the weekly granularity, but the existing text covers the essential information.

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

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

Schema coverage is 100%, with each parameter having a description in the schema. The description text does not add any additional meaning beyond what the schema provides (e.g., no explanation of region codes or weeks default). Given high schema coverage, baseline 3 is appropriate.

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

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

The description uses specific verb 'track' and resource 'weekly inventory changes', clearly stating what the tool does. It lists the specific trend metrics returned (inventory, new listings, days on market, median price, price reductions), distinguishing it from sibling tools like altos_active_listings which likely provide a snapshot rather than 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?

The description implies usage for tracking weekly inventory trends via the example region 'Austin, TX' and the focus on changes over time. However, it does not explicitly state when to use this tool versus alternatives (e.g., altos_market_stats for broader market stats) or mention any prerequisites or conditions. The guidance is implied but not direct.

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 aligns with annotations (readOnlyHint, idempotentHint, destructiveHint). It does not add behavioral traits beyond what annotations already provide, and no additional context (e.g., authentication needs, pagination) is given. With rich annotations, a score of 3 is appropriate.

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

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

The description is extremely concise, comprising two short sentences (11 words). It is front-loaded with the core purpose and wastes no words.

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

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

Given the presence of an output schema (stated), the description does not need to detail return values. It covers the primary functionality. Minor omission: it could mention the need for an API key, but that is in the required schema. 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?

Schema coverage is 100%, so the input schema already documents all parameters. The description does not add parameter-specific information, and the baseline is 3. No additional value beyond schema is provided.

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

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

The description clearly states the verb 'Browse' and the resource 'downloadable regional real estate data files'. It also mentions the output type 'catalog with file names, formats, and descriptions', which distinguishes it from sibling tools that focus on specific data types.

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

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

The description implies usage for browsing available files but does not provide explicit when-to-use or when-not-to-use guidance. No alternatives are mentioned, though the sibling context shows other tools for specific data retrieval.

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

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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds value by listing the return fields (inventory count, new listings, median price, etc.) and clarifying it's a 'current' snapshot, though it doesn't mention the date parameter or that data defaults to the most recent Friday.

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

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

Two sentences, front-loaded with the purpose, no fluff. Every sentence adds value: the first states the action and region example, the second lists the return metrics. Perfectly concise.

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

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

Given the presence of an output schema (not shown but stated) and 5 parameters with full schema descriptions, the description is mostly complete. However, it omits mention of optional parameters (date, quartile, res_type) and could clarify that the snapshot can be for a specific past Friday. Still, it provides a solid overview.

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

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

Schema coverage is 100%, so the baseline is 3. The description does not add extra meaning beyond the schema; it only provides a region example but doesn't explain region codes or other parameters like date, quartile, or res_type. No additional semantic 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?

The description clearly states the tool gets a 'current market snapshot' for a region and lists specific metrics (inventory, new listings, median price, days on market, market action index). This distinguishes it from sibling tools like altos_active_listings or altos_inventory_trend, which focus on specific listing types or 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?

The description does not provide explicit guidance on when to use this tool versus siblings. It implies it's for a broad overview, but no 'when to use' or 'when not to use' is stated, which would help an agent choose between similar tools.

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

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

Annotations already declare readOnlyHint=true, idempotent=true, destructiveHint=false, so the tool is clearly safe. The description adds value by specifying the freshness window ('under one week') and listing the returned fields (address, price, beds, baths, listing date). No contradiction with annotations.

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

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

The description is a single, efficient sentence that conveys the core purpose. It is front-loaded and contains no wasted words.

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

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

Given that the tool has an output schema (not shown but present), the description adequately summarizes key return fields. It does not explain pagination or default behavior, but for a simple listing tool this is 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?

Schema coverage is 100%, with all four parameters described in the schema. The description does not add any additional meaning or examples beyond the schema, 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?

The description clearly states the tool gets 'freshly listed properties (under one week on market)' for a region, specifying the verb, resource, and time constraint. It does not explicitly differentiate from sibling tools like altos_active_listings, but the purpose is unambiguous.

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

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

The description provides an example region but gives no guidance on when to use this tool versus alternatives (e.g., altos_active_listings, altos_pending_sales). No when-to-use or when-not-to-use context is provided.

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, so the safety profile is clear. The description adds that it returns specific fields, but lacks details on pagination, rate limits, default limits, or that the date parameter must be a Friday.

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

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

The description is a single, front-loaded sentence that states the purpose and key return fields with no redundant words.

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

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

The description omits important context: the region example 'Miami, FL' contradicts the schema's expected format (e.g., 'ca_los-angeles' or 'ca_94105'). It also does not mention the date parameter, default limit, or that results may vary due to openWorldHint. Although an output schema exists, the description should still set correct expectations.

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

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

Input schema covers all 4 parameters with descriptions, so baseline is 3. The description adds a natural language example ('Miami, FL') but this is potentially inconsistent with the schema which expects region codes like 'ca_los-angeles'. No additional parameter semantics are provided.

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

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

The description clearly states it finds 'properties under contract in a region', providing a specific verb and resource. It also lists returned fields (address, price, beds, baths, days pending), which distinguishes it from sibling tools like 'altos_active_listings' that likely return different statuses.

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

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

No guidance is provided on when to use this tool versus alternatives such as 'altos_active_listings' or 'altos_new_listings'. There is no discussion of prerequisites, when not to use, or trade-offs.

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

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

Annotations indicate readOnly, openWorld, idempotent, and non-destructive. The description goes beyond by explaining the tool routes to other tools, fills arguments, and returns stable citation URIs. It adds context about the meta-tool nature and output format, which is valuable for agent understanding.

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 a bold preference statement, followed by a list of use cases, then a functional explanation, and finally examples and signal words. It is longer than necessary but well-structured and 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 mentions 'structured answer with stable pipeworx:// citation URIs', providing a clear output expectation. It covers the tool's scope, usage signals, and examples, making it sufficiently complete for an agent to decide when to invoke it.

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

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

Schema coverage is 100% with all parameters as aliases for 'question'. The description only briefly notes the aliases, adding minimal new information beyond the schema. The schema already describes each parameter well, so a 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 routes questions to thousands of tools across verified sources and returns structured answers with citations. It lists specific domains (SEC filings, FDA drug data, etc.) and distinguishes itself from web search with 'PREFER OVER WEB SEARCH'.

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

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

The description explicitly advises using this tool over web search for factual, structured queries. It provides signal words like 'what is', 'look up', 'find', and concrete examples. It does not explicitly state when not to use it, but the context implies it is for authoritative data, which is sufficient guidance.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. Description adds that it costs one extra LLM call vs ask_pipeworx, and details refusal reasons and return structure. 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 detailed and informative but somewhat verbose. It front-loads purpose, but includes extensive return format details that could be structured more concisely. Still clear.

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

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

Given no output schema, the description thoroughly documents return fields (answer, evidence, confidence, source, fetched_at, refusal_reason) and all refusal scenarios. It also covers the extra cost and routing. 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%, but description adds little beyond stating 'Your question in natural language' and listing aliases. The parameter meaning is already clear from the schema, so baseline 3.

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

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

The description clearly states it is a 'hallucination-resistant answer mode for high-stakes reads' and explains the process: picks tool, fills arguments, fetches data, extracts answer using only tool result. It distinguishes from ask_pipeworx by the grounded extraction step, ensuring no fact invention.

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

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

Explicitly states when to use: 'when an answer will be quoted, cited, or acted on, and the agent must not invent facts' and lists example domains. Also advises to prefer ask_pipeworx for casual lookups, providing clear alternatives.

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

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

Annotations already declare readOnlyHint, idempotentHint, etc., but the description adds extensive behavioral details: resolution process (resolver contract, match confidence), safety short-circuits (low-confidence, closed markets), tradeability warnings, and resolution-rule risk. 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 very long and comprehensive, but suffers from verbosity. It front-loads the main purpose but then dives into many edge cases and internal implementation details (e.g., resolver contract, parent event extractor). While all information is valuable, it could be more concise without losing meaning.

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 lack of output schema, the description thoroughly explains response shapes (market, analysis, evidence), resolver behavior, parent event extraction, news fields, and risk factors. This covers all needed context for an agent to use the tool correctly and interpret results.

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

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

Schema description coverage is 100% with clear parameter descriptions. The description further elaborates on parameter behavior (e.g., 'quick' vs 'thorough' fan-out, 'include_raw' with size implications) and provides concrete examples, adding significant value beyond the schema.

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

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

The description clearly states the tool researches a Polymarket bet by pulling Pipeworx data. It specifies input types (slug, URL, question text) and gives explicit use cases like 'should I bet on X'. It distinguishes itself from sibling tools by focusing on single-bet research with fan-out evidence.

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

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

The description provides clear when-to-use guidance ('Use for...') and lists many examples. However, it does not explicitly mention when NOT to use this tool or specify alternative sibling tools (e.g., polymarket_edges) for related tasks, which would improve 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 readOnly, openWorld, idempotent, and non-destructive. Description adds significant behavioral context: real-time data from SEC EDGAR/XBRL, off-calendar fiscal year handling, citation URIs, and sorting by primary metric.

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

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

Description is front-loaded with triggers and is efficient, but slightly long. Every sentence adds value with examples and clarifications.

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

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

Given complexity (two entity types, multiple data sources), description covers purpose, data pulled, handling of edge cases (off-calendar fiscal years), and output details (paired data, citations). No output schema exists, but description sufficiently explains what is 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 covers both parameters (type and values). Description adds meaning with examples (tickers for companies, drug names for drugs), max/min items, and result behavior (sorted by primary metric). 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 clearly states it performs side-by-side comparison of 2-5 companies or drugs, with specific natural language triggers. It distinguishes from sequential lookups and explains the data sources for each entity type.

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' and provides context for when to use. Lacks explicit when-not-to-use or alternatives, but the preference is clear.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive. The description adds useful behavioral context: expected timing (15-60s), that it never invents answers (gaps[]), and that facts arrive pre-verified. No contradictions. Could have mentioned potential costs or rate limits beyond plan.

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

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

Description is front-loaded with key actions and benefits, followed by usage guidance, requirements, and timing. Every sentence adds essential information with no redundancy. Efficiently packs a lot without being verbose.

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

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

Given the tool's complexity and lack of output schema, the description explains the return format (structured findings packet with gaps[] and citations). It covers input nature, parallel processing, and account requirements. Minor gaps: no mention of error handling or input limits.

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

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

Schema description covers both parameters 100%. The description adds context: 'broad/multi-part is fine' for question, and explains depth values (quick=3, standard=5, thorough=8). This enhances meaning beyond the schema itself.

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 grounded multi-source research by decomposing questions and routing to 3,751 tools in parallel. It contrasts with sibling tool 'ask_pipeworx' for single lookups, establishing a distinct purpose.

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

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

Explicitly recommends use for broad or multi-part questions and advises using 'ask_pipeworx' for single lookups. Also notes account requirement and that 'thorough' depth needs a paid plan, providing clear when-to-use and when-not-to-use guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds value by explaining that results include full input schemas with curated examples ready to call directly, no second lookup needed. This provides behavioral context beyond annotations.

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

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

Description is one paragraph, front-loaded with purpose and usage. Every sentence adds value, listing example domains and explaining return behavior. Could be slightly more structured but is efficient.

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

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

Despite no output schema, description fully explains return value: top-N most relevant tools with names, descriptions, and full input schemas. It also notes real-time ready-to-call format. No missing critical information for a search/discovery tool.

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

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

Schema description coverage is 100%, so baseline is 3. Description adds context by noting aliases (task, q, description, search) and giving natural language examples. However, it doesn't elaborate on limit behavior or query format beyond schema.

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

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

Description clearly states 'Find tools by describing the data or task' with specific verb-resource. It distinguishes itself from sibling tools by being a meta-tool for discovery, explicitly stating 'Call this FIRST' to see available options.

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

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

Explicitly tells when to use: 'when you need to browse, search, look up, or discover what tools exist' and gives concrete examples like SEC filings, FDA drugs. It also advises 'Call this FIRST when you have many tools available and want to see the option set,' providing clear context.

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

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

Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint) are present. The description adds behavioral context: it fans out across multiple sources, mentions the USPTO PatentsView API sunset May 2025 with soft-fail behavior, and lists the return fields. This enhances transparency beyond annotations.

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

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

The description is detailed and front-loaded with examples, but it is somewhat lengthy. Every sentence adds value, but it could be slightly more concise. Overall, it is well-structured.

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

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

Given the complexity of aggregating multiple sources and no output schema, the description provides a comprehensive list of what is returned (cik, company_name, recent_filings, fundamentals, patents, news, LEI). It also notes limitations (patents soft-fail) and input constraints. This is complete for the tool's purpose.

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 both parameters described. The description reinforces the parameter semantics by clarifying that type is only 'company' and value accepts ticker or zero-padded CIK, and explicitly states that names are not supported (referencing resolve_entity). It adds practical usage patterns.

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

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

The description starts with example queries like 'Tell me about X' and explicitly states it provides a 'full cross-source profile of a US public company in ONE parallel call.' It details the specific sources (SEC EDGAR, XBRL, USPTO, news, GLEIF) and return fields, clearly distinguishing from sibling tools like resolve_entity and compare_entities.

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

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

The description says 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view' and advises to use resolve_entity first if only a name is available. This provides explicit when-to-use and when-not-to-use guidance.

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

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

The description mentions deletion and clearing sensitive data, which aligns with annotations. However, annotations already provide destructiveHint and idempotentHint, so the description adds minimal extra behavioral context.

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

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

Two sentences, front-loaded with the action, 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?

For a simple tool with one parameter and no output schema, the description covers purpose, usage, and context. Could mention return value or confirmation, but not critical.

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

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

Schema coverage is 100% with the parameter 'key' described as 'Memory key to delete.' The description does not add meaning beyond the schema, so baseline 3.

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

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

The description clearly states 'Delete a previously stored memory by key,' using a specific verb and resource. It distinguishes from siblings by mentioning '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?

Explicit guidance is given: 'Use when context is stale, the task is done, or you want to clear sensitive data.' It also pairs 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 declare readOnly, openWorld, idempotent, non-destructive. The description adds context about fetching an external URL, extracting data, and emitting markdown, aligning with annotations. It could mention error handling or rate limits but is sufficient.

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

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

The description is three sentences: purpose/outcome, process, use cases. No fluff, front-loaded with core information, every sentence adds value.

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

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

Given no output schema, the description explains the output format ('single text blob ready to drop at site-root/llms.txt') and process. For a simple tool with two parameters, this is complete.

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

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

Schema covers both parameters with descriptions (100% coverage). The description does not add significant new parameter info beyond the schema, 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 the tool generates an llms.txt file for a URL, specifying the action (fetch, extract, emit) and output format. It distinguishes itself from sibling tools (no other llms.txt generator) and includes a clear purpose: AI indexing.

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 (client site indexing, personal projects, competitor audits) and implies when to use. It does not explicitly mention when not to use or alternatives, but no direct sibling alternative exists.

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

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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description's behavioral transparency is partially covered. The description adds return field details but doesn't go beyond annotations in terms of side effects or auth needs.

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. The first sentence specifies the action and return values; the second gives usage guidance. Every sentence is purposeful and front-loaded.

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

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

For a simple list tool with one optional boolean parameter, the description covers purpose, return schema, and usage context. Annotations cover safety. No gaps or missing information.

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

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

Schema coverage is 100%, and the parameter 'include_inactive' has a description in the schema. The tool description does not add additional meaning beyond what the schema provides, 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?

The description clearly states the tool lists the caller's active subscriptions and specifies the return fields (id, type, params, etc.). It also provides usage context to distinguish from sibling tools like subscribe and unsubscribe.

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

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

The description explicitly says when to use the tool: 'review what you're monitoring before adding more or to find an id to cancel.' It gives clear context without explicitly stating when not to use, but given sibling tools, it's adequate.

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 behavioral traits beyond annotations: rate-limited to 5 per identifier per day, free, doesn't count against tool-call quota. Annotations indicate non-read-only and non-destructive, which matches the description. No contradiction.

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

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

Description is concise yet comprehensive, using six sentences to cover purpose, usage, constraints, and formatting. 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 tool has 3 parameters (one nested), no output schema, and no complex output, the description fully covers what the agent needs to know: when to use, how to structure feedback, and what constraints apply.

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

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

Schema coverage is 100%, but description adds value by explaining the enum meanings in more detail, elaborating on context subfields, and providing guidance on message specificity and length limits.

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's purpose: sending feedback to Pipeworx team about bugs, missing features, or praise. It distinguishes itself from sibling tools like data retrieval or analysis tools, which are not for 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 states when to use the tool: for bugs, feature requests, data gaps, or praise. Also provides guidance on what not to do (don't paste end-user prompts) and mentions rate limits and quota.

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

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

Annotations already show read-only, idempotent, open-world. Description adds data source (CF analytics-engine), no PII, caching behavior (5min-1h), and output structure. 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, front-loaded with the main action, then use cases, then technical details. Every sentence adds value with no redundancy.

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

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

Given no output schema, the description explains the return type (top tools, packs, count) and sketches the tuple format. Could specify output more precisely, but adequate for a simple tool.

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

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

Schema covers the one parameter fully with enum and description. Description adds semantic guidance on window selection ('hot right now' vs 'steady-state demand'), providing extra 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 returns trending data (top tools, packs, call volume) over a window. It uses specific verbs and resources, and distinguishes itself from siblings like discover_tools by focusing on current popularity.

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 concrete use cases are listed, explaining when to use the tool. However, it does not explicitly mention when not to use it or compare to alternatives, though the function is self-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 indicate safe, read-only, idempotent behavior. Description adds critical behavioral details: fill check against live depth, semantic anchor (Jaccard similarity ≥0.30), partition filter (placeholder slugs dropped), and edge cases like non-tradable overrounds. 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?

Moderately long but well-structured: front-loaded with requirement, then explains modes, then edge cases. Every sentence adds value (fill check, similarity anchor, partition filter). Could be slightly more concise, but information density is high.

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

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

Given the tool's complexity (two modes, multiple filters, output structure), the description is thorough. It covers response format (opportunities[], partition_check, fill_check), failure modes (skipped_low_similarity, placeholder fraction), and prerequisites. No output schema, but description sufficiently explains return values.

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

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

Schema covers both parameters with descriptions. Description adds meaning: explains accepted formats (slugs or URLs), distinguishes event vs topic behavior, and highlights cross-event scanning capabilities. Schema coverage is 100%, so baseline is 3; the extra context justifies a 4.

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

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

Describes a specific verb ('Find arbitrage opportunities') on a specific resource ('Polymarket') using distinct methods (monotonicity violations + partition-sum checks). Clearly distinguishes two modes (event vs topic), each with concrete examples.

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 required parameters ('REQUIRES one of `event` OR `topic` — call with no args fails'), recommends when to use each mode, and provides exclusion guidance (e.g., 'cross-event mode catches patterns that single-event misses'). Also mentions fill check to avoid non-tradable opportunities.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds rich behavioral context: 1h caching keyed on all knobs, details of model families and their computations (lognormal barrier, GDELT volume ratio, partition_overround with per-sport alpha, placeholder filtering), and response structure including diagnostic fields. 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 categories (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT) and detailed explanations. Front-loads purpose then details each segment, parameters, and response. Every sentence adds value, but could be slightly more concise (e.g., combining some technical details).

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, fed_candidates/fed_note, _diagnostics with funnel counters, category_counts, filter_skips). Covers all components for a complex 9-parameter tool, ensuring agents understand what to expect.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaningful extra context for every parameter (e.g., min_kelly 'Skips opportunities that are too small', max_spread_pp 'anything wider eats most plausible edges', min_partition_leg_kelly explains partition arbs always return 0 at parent level). Goes significantly beyond schema descriptions.

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

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

The description clearly states the tool scans Polymarket markets for opportunities where Pipeworx data disagrees with market price, explicitly framing it as 'what should I bet on today'. It distinguishes from sibling tools like polymarket_arbitrage and polymarket_kalshi_spread by focusing on Pipeworx data disagreement.

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

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

The description provides usage context (discovery without paging hundreds of markets, tradeable-edge knobs, caching), but does not explicitly state when NOT to use this tool or compare to alternatives. It lacks exclusions or conditional advice for specific scenarios.

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

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

Annotations already declare readOnly, openWorld, idempotent, non-destructive. The description adds critical behavioral details: data from daily snapshots, bounded by 60-day TTL, decay computed on daily closes not intraday, and gap handling. Contradicts nothing.

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 question, then details the response structure and limits. Every sentence serves a purpose; no fluff. Well-organized with clear sections.

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

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

With no output schema, the description fully documents the response: tracked (with full time-series, first_seen, trend, decay), expired (with lifespan_days), and snapshot_dates. It also explains limits like 60-day TTL and snapshot gaps. Extremely complete for an AI agent.

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

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

Input schema has 100% coverage (both parameters described). The description adds default values (days=14, window='1wk'), clamp range for days, and explains how parameters affect the response (e.g., 'latest snapshot'). 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: 'answers how long has this edge existed and is it shrinking?' It provides a specific verb-resource pair (track edge persistence) and distinguishes itself from sibling tools like polymarket_edges by focusing on time-series and trend analysis.

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 (comparing fresh vs old edges) and explains the response structure. However, it does not explicitly exclude alternatives or mention when not to use it, though the context of sibling tools is available.

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, idempotentHint, destructiveHint. The description adds critical context about walking the ladder, returning fields like top_of_book, vwap_fill_price, slippage_pp, and importantly warns about the risks of partial basket fills leading to unhedged directional positions. This significantly exceeds the annotation coverage.

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 section headers for SINGLE-MARKET and BASKET, making it easy to scan. It front-loads the purpose and usage. Although somewhat dense, each sentence adds meaningful information.

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

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

Despite having no output schema, the description comprehensively lists all return fields for both modes and explains why the tool is important (e.g., dominant loss mode in arb bots). It covers the complexity of two modes thoroughly.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds value by clarifying how size_usd is interpreted differently in basket mode (settlement notional) and the auto logic for side in basket mode. 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 clearly states it performs a realizable-vs-theoretical edge check against live CLOB order-book depth. It specifies two distinct modes (single-market and basket) and clearly differentiates from sibling tools like polymarket_arbitrage by positioning itself as a prerequisite check.

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

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

Explicitly states when to use: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500'. It also implies when not to use (small trades). No explicit alternatives are listed, 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 indicate readOnly, idempotent, openWorld. The description adds extensive behavioral context: two modes, response structure (leg prices, top spreads), safety fields (compatibility_warning, temporal_alignment), and detailed counters for skipped comparisons. It goes far beyond the annotations.

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

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

The description is longer but well-structured with clear sections and bullet-like formatting. It is front-loaded with the core concept and every sentence adds necessary detail. Slightly dense but appropriate for the complexity.

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

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

Despite no output schema, the description fully specifies the response components (leg prices, top spreads, safety fields) and explains edge cases like compatibility warnings. The tool is complex, and the description covers all necessary aspects for correct invocation.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds meaning by explaining the topic shortcuts, how explicit parameters override, and how the two modes interact, which is valuable 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 computes cross-venue spread between Kalshi and Polymarket. It distinguishes itself from sibling tools like 'polymarket_arbitrage' by focusing on cross-venue comparison rather than intra-venue arbitrage. The two modes (topic shortcuts and explicit tickers) are precisely defined.

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

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

The description explains when to use each mode and warns that most pre-mapped topics currently return a compatibility_warning, setting realistic expectations. It does not explicitly contrast with other tools, but the context is sufficient given the sibling list.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds useful context beyond annotations, such as the dual behavior (retrieve vs list all) and scoping to identifier. 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?

The description is three sentences with no fluff. First sentence states core function, second gives usage guidance, third adds scoping and pairing. Efficient and well-structured.

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

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

For a simple read-only key-value retrieval tool with one optional parameter and no output schema, the description covers the retrieval, listing, scoping, and pairing with related tools. It is 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% for the single optional 'key' parameter, with a clear description. The description adds the note 'omit the key argument' which matches the schema, but does not add significant new meaning beyond what the schema provides.

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

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

The description clearly states the verb 'Retrieve' and the resource 'a value previously saved via remember', and distinguishes itself from sibling tools like 'remember' and 'forget'. It also explains the dual behavior of retrieving a specific key or listing all keys.

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: 'Use to look up context the agent stored earlier... without re-deriving it from scratch.' It also notes scoping and pairing with remember/forget. However, it does not explicitly state 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?

The description discloses key behaviors beyond annotations: setting mark_read flags events as read and alters future results. It also mentions the feed is persisted and accessible via GET endpoint. Annotations already declare readOnlyHint=true, but the description clarifies the side effect 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 four well-structured sentences, front-loaded with the main purpose. Every sentence adds value with no redundancy or fluff, making it efficient and easy to parse.

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

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

Despite no output schema, the description specifies return fields (source, citation_uri, raw event payload). It covers usage details (filtering, marking read, polling) and provides an alternative access method. All necessary context is present.

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 meaningful explanation: provides an example for type ('sec_8k'), clarifies that since is an ISO timestamp for filtering, and explains mark_read's effect on subsequent calls. This enhances the schema descriptions.

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

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

The description clearly states it pulls fired events from a subscription feed and returns the most recent alerts with specific fields. It distinguishes itself by mentioning an alternative access method (GET endpoint) and implies its role among sibling tools focused on alerts and 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 tells when to use the tool (to get recent alerts, filter by type/since, set mark_read) and states that polling works fine. It does not explicitly exclude scenarios or compare with sibling tools, but it provides sufficient context for appropriate 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 provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. The description adds substantial behavioral context: fan-out to multiple sources, GDELT→GNews fallback, USPTO soft-fail, date format acceptance, and return structure. No contradiction with annotations.

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

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

The description is a single dense paragraph but is front-loaded with example queries. It is informative without extraneous words, though slightly dense. A short bullet list might improve readability, but it remains 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 the tool's complexity (multiple sources, fallback, date formats), the description covers all essential aspects: sources, fallback behavior, date formats, return structure, and when to use alternative tool. No output schema exists, but the return structure is described sufficiently.

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

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

Schema coverage is 100% with descriptions. The description adds value by providing examples for 'since' (ISO date and relative shorthand) and clarifying 'value' accepts ticker or CIK. This enhances understanding beyond the schema.

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

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

The description clearly states the tool provides a 'change feed for a company in the last N days/weeks/months' and gives example queries like 'what's new with X'. It distinguishes from sibling 'entity_profile' by directing when to use that tool instead.

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

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

The description gives explicit guidance: it shows example queries, explains the data sources and fallback, and directly tells when to use 'entity_profile' instead for static profiles. This clearly differentiates from alternatives.

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

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

Annotations declare write, idempotent, non-destructive. Description adds scoping ('by your identifier') and persistence details (persistent for authenticated, 24h for anonymous), which go beyond annotations. No contradiction.

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

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

Three sentences, front-loaded with purpose, no fluff. Efficient and informative.

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

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

For a simple 2-param tool with no output schema, description covers purpose, usage, behavioral traits, and sibling pairing. 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 with descriptions for key and value. Description adds context like examples and value types, slightly enhancing semantics beyond schema.

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

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

Clearly states 'Save data the agent will need to reuse later' with specific verb and resource. Distinguishes from siblings recall and forget, and provides concrete examples (ticker, address, preference).

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

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

Explicitly says 'Use when you discover something worth carrying forward' and pairs with recall/forget. No explicit when-not-to-use, but positive guidance is strong.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds significant behavioral context: it cascades through lookup endpoints, auto-disambiguates company names, and returns specific fields with 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 front-loaded with examples and a clear purpose statement. It contains useful details without being overly verbose. A slight trim could improve conciseness, but all sentences earn their 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 complexity (two entity types, no output schema), the description covers return fields and citation URIs for each type. It lacks mention of error handling or rate limits, but the annotations cover safety. Overall, it provides sufficient context for correct invocation.

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

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

Schema coverage is 100%, but the description adds substantial meaning beyond the schema. It provides concrete examples for the 'value' parameter (e.g., AAPL, 0000320193, ozempic) and details what each 'type' returns, including the citation URIs, which the schema does not convey.

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

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

The description uses specific examples like 'What's the ticker for...' and explicitly states the purpose: 'resolve a user-spoken NAME to the canonical/official identifier other tools require as input.' It clearly distinguishes itself from sibling tools by acting as a gateway for identifier 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 'Use FIRST whenever you have a name but need an ID.' It provides clear context on when to use the tool and explains that it replaces 2-3 manual lookups. However, it does not explicitly mention when not to use it or list alternatives, which prevents a perfect score.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is clear. The description adds context about probing each entity with ai_visibility_check and returning a ranked list with score, confidence, signal density. No contradiction.

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

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

Two sentences with no wasted words. The first sentence front-loads the core purpose ('Compare AI visibility across multiple entities side-by-side'). Every sentence earns its place.

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

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

Given 4 parameters (1 required), no output schema, and annotations that cover safety, the description sufficiently explains input behavior and output format ('ranked list with score, confidence, signal density'). Could elaborate on return shape slightly but is complete enough for this simple tool.

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

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

Schema coverage is 100%, so the schema already documents parameters. The description adds meaning by explaining that the first entity is treated as 'subject' for narrative and that context disambiguates common names. 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 uses a specific verb 'Compare' with clear resource 'AI visibility across multiple entities' and outcome 'ranks by score'. It distinguishes from sibling tools like ai_visibility_check (single entity) and compare_entities (generic comparison) by specifying the probing mechanism and ranking.

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 ('competitive AI-marketing audits') with an example question. It implies when to use but does not explicitly state when not to use or provide alternatives beyond the example.

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 significant value beyond annotations: it details partial failures (bundlephobia timeout), graceful degradation, and the structure of the response. No contradiction with annotations (readOnlyHint, etc.).

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

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

The description is a single paragraph but well-structured, front-loading the main purpose. It is informative without being overly verbose, though could be slightly more concise.

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

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

Despite no output schema, the description thoroughly explains the return values (summary block fields, per-advisory detail, links, alternative versions) and error handling (partial failures). Complete for a complex composite tool.

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

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

Schema coverage is 100% with good parameter descriptions. The description adds context (scoped packages accepted, version defaults to latest), providing slight additional 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 it is a composite check for npm packages, covering license, advisories, version history, and bundle size. It distinguishes itself from sibling tools by being a one-call aggregation and specifies the scope (NPM only) and alternatives for other ecosystems.

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

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

Explicitly states when to use: when an agent asks about safety, popularity, size, or cost of adding a package. Mentions alternatives (deps.dev:version for other ecosystems) and explains limitations (bundlephobia timing issue).

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, etc.), the description details internal mechanics: embeddings, cosine similarity, 500-char overlapping windows, 200K char cap with truncation flagging, and output format with offsets.

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, front-loaded with purpose and usage, then technical details. Every sentence adds value without redundancy.

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

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

Despite no output schema, the description fully explains output format (passages with offsets and scores), truncation behavior, and integration with sibling tools, covering all necessary context.

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

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

Schema covers all 3 parameters, and description adds illustrative examples (e.g., SEC 10-K, natural language query) and explains the limit parameter indirectly via 'top-N', adding practical 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?

The description clearly states the tool performs semantic search within a fetched record, distinguishing it from siblings like ask_pipeworx_grounded by explaining the use case and pairing.

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

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

Explicitly states when to use: when the record is too large for the prompt, and how it pairs with ask_pipeworx_grounded for grounded generation, providing clear context vs alternatives.

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

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

Annotations indicate idempotentHint=true and readOnlyHint=false. The description adds context: requires authenticated account, returns subscription id, delivery channel specifics (webhook signing, auto-disable after 10 fails, SMS cap). It does not clarify idempotency or cost implications, but overall adds value beyond annotations.

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

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

The description is front-loaded with the main action and return value, then structured into requirements, supported types (with examples), and delivery channels. 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?

The description covers the input parameters thoroughly and mentions the return value (subscription id). It does not describe error scenarios or what happens on duplicate subscription, but given the complexity and presence of annotations, it is adequately complete.

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

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

With 100% schema coverage, the description significantly enriches parameter meaning with specific examples for each subscription type and delivery channel, including item codes, topics, and webhook mechanics that are not present in the schema descriptions.

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

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

The description clearly states the verb 'Create' and the resource 'subscription to a live-data event stream', and distinguishes from siblings like list_subscriptions and unsubscribe by specifying it returns a new subscription id and is for proactive monitoring.

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 (proactive monitoring) and includes a prerequisite (Pipeworx OAuth account). It implicitly distinguishes from sibling tools but does not explicitly state when not to use or provide alternatives.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds context about the output structure (category-bucketed examples) but does not introduce new behavioral traits beyond what annotations provide. It does not mention any side effects or limitations.

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

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

The description is well-structured with bullet points and front-loaded key phrases. Every sentence adds value, and it is appropriately sized for the complexity of the tool.

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

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

Given no output schema, the description explains the return format (categorized examples with tool+argument shapes) and mentions the live catalog. It provides sufficient context for an agent to use the tool correctly. Could be slightly more explicit about the idempotency.

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 covers the single parameter with a description. The description adds value by clarifying the optional nature and that omitting the topic yields a cross-category spread. This goes beyond the schema description.

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

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

The description clearly states the tool's purpose: providing example questions categorized by topic, each with exact tool and argument shapes. It distinguishes itself from siblings like ask_pipeworx and discover_tools by specifying that it's the onboarding entry point to learn what Pipeworx can do.

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

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

Explicitly states when to use: 'Use this FIRST when you do not yet know what Pipeworx can do for you.' Also explains how to call it with no arguments or topic. However, it could be more explicit about when not to use it (e.g., if the agent already has a specific question).

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 significant context beyond annotations: explains that the row is deactivated (not deleted) and how historical events are preserved. Ownership enforcement is also disclosed. Annotations already indicate non-destructive and idempotent, and the description aligns perfectly.

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

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

Two short sentences, each essential. Front-loaded with the core action. No redundancy or wasted words.

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

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

For a single-parameter tool with no output schema, the description fully explains the behavior, ownership rule, and side effects. Complete and self-contained.

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

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

Schema covers the parameter with description, but the description adds contextual value by stating that the subscription must be owned by the caller. With 100% schema coverage, the description provides meaningful extra guidance.

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

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

The description clearly states the action ('Cancel a subscription by id') and distinguishes from siblings like 'subscribe' and 'list_subscriptions' by specifying the ownership enforcement and deactivation behavior.

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

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

Provides clear usage context: only own subscriptions, requires correct id. Mentions that historical events remain available, which informs when to use this tool over deleting. Lacks explicit mention of alternatives but sufficient for a simple 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds behavioral context by listing the return verdict types, structured output, citation, and percent delta. It also highlights that it replaces multiple sequential calls. No contradictions with annotations.

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

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

The description is well-structured, starting with trigger phrases, then purpose, domain, return details, and value proposition. Every sentence adds value, though it is slightly lengthy. It is organized and front-loaded with key 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 adequately describes return values. It specifies the domain and notes the tool replaces multiple calls. However, it could mention limitations (e.g., only for public US companies) or prerequisites more explicitly, but overall it is fairly complete.

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

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

The input schema has 100% coverage for 'claim', and the description enriches it with natural-language examples and expected formats (e.g., 'Apple's FY2024 revenue was $400 billion'). This goes beyond the schema to clarify what a valid claim looks like.

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 as 'natural-language claim verification against authoritative sources' and provides concrete examples. It distinguishes itself from sibling tools by noting it replaces 4-6 sequential calls, making it clear what unique value it offers.

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

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

The description clearly says to use when the agent needs to check factual correctness and specifies the domain (company-financial claims). However, it does not explicitly state when not to use it or mention alternative tools for non-financial claims, which would improve guidance.

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