Onedrive

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

Annotations already cover safety (read-only, idempotent, non-destructive). The description adds valuable behavioral context: that the default model is free, Anthropic requires a user-provided API key (cost implications), and the return structure per model. It does not contradict annotations.

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

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

The description is concise (4 sentences), front-loaded with the core purpose, and every sentence adds value. There is 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?

Given the tool's complexity (multi-model probing, scoring), the description covers the main function, input/output, default behavior, and optional extensions. It lacks output schema but describes the return structure sufficiently. Annotations and schema cover the rest. Complete for the intended use.

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

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

Schema coverage is 100%, but the description adds meaning beyond the schema: it explains the default model, that `models` can be omitted, that `_apiKey` is only needed for Anthropic, and provides examples for `entity` and `context`. This enriches the agent's understanding of parameter usage.

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

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

The description clearly states the tool probes LLMs for knowledge about an entity and returns a visibility score. It provides specific use cases (AI-marketing audits, pre-launch brand checks, competitive monitoring) and distinguishes itself from sibling tools like `scan_competitor_ai_presence` by being more general.

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

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

The description gives clear usage context (when to use) and explains the default model and optional Anthropic probe. However, it does not explicitly state when NOT to use or compare with very similar siblings like `scan_competitor_ai_presence`, but the provided use cases are sufficient.

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

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds valuable context: the tool routes to 3,272 tools across 728 verified sources and returns pipeworx:// citation URIs. While no negative traits (e.g., rate limits) are disclosed, the description significantly expands on the annotations without contradiction.

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

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

The description is front-loaded with the key directive and provides rich examples, but it is somewhat verbose (multiple sentences, lengthy comma-separated lists). The level of detail is justified by the tool's complexity, but a slightly more concise version would be ideal.

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 complex tool that routes to many sources, the description covers purpose, usage guidance, and output format (structured answers with citations). It does not mention potential limitations like latency or cost, but the overall coverage is good. No output schema exists, so the description compensates adequately.

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

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

Schema coverage is 100%, so the schema itself documents all parameters (including aliases). The description only provides high-level guidance (natural language question) but does not add parameter-specific details beyond what the schema already offers. A score of 3 is appropriate given the high schema coverage.

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

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

The description clearly states the tool's purpose: routing natural language questions to thousands of curated data sources and returning structured answers with citations. It explicitly distinguishes itself from web search and lists many use cases (SEC filings, FDA data, etc.), making the purpose unmistakable.

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

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

Provides explicit guidance: 'PREFER OVER WEB SEARCH' for factual questions about real-world data. Lists example query patterns ('what is', 'look up', 'find', etc.) and concrete examples (e.g., 'current US unemployment rate'), leaving no doubt about when to use this tool.

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

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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds extensive behavioral details: fan-out to multiple data sources, safety short-circuiting, resolver confidence checks, and error handling for news fallbacks. There is 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 quite long and includes detailed fan-out examples and response shapes. While well-structured with sections, it could be more concise by summarizing some examples. However, every sentence adds value for a complex 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 the complexity and no output schema, the description comprehensively covers return values (market, analysis, evidence), resolver contract, parent event extractor, news fields, and edge cases (low-confidence, closed markets). It leaves no significant gaps.

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

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

Schema coverage is 100%, and the description adds meaning by explaining the depth enum ('quick' vs 'thorough'), market input formats, and include_raw default. It provides examples and default behavior, which is valuable for correct invocation.

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

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

The description clearly states the tool researches Polymarket bets by pulling relevant Pipeworx data. It uses a specific verb ('Research') and resource ('Polymarket bet'), and distinguishes from sibling tools like polymarket_arbitrage by focusing on evidence-gathering for bet decisions.

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

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

The description explicitly says 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z"'. It also mentions when not to trust the analysis (e.g., low-confidence matches, closed markets). However, it does not explicitly compare to sibling tools for when to use 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, destructiveHint=false. The description adds significant behavioral details: data sources (SEC EDGAR/XBRL, FAERS, FDA), specific financial metrics, handling of off-calendar fiscal years, and sorting by primary metric. 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 yet comprehensive, front-loading purpose and usage, then method details. Each sentence adds value without redundancy. Appropriate length for the tool's 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 lacking an output schema, the description explains the return format ('paired data + pipeworx:// citation URIs') and sorting behavior. Covers both entity types thoroughly. No missing information for effective use.

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

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

Input schema already covers 100% with descriptions for both parameters. The description adds context: explains type enum values and values array constraints with examples (e.g., tickers vs drug names, max 5). Credit for adding meaning beyond schema.

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

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

The description states a clear verb-resource pair ('compare 2-5 companies or drugs side by side') and explicitly lists use cases like 'compare X and Y', 'X vs Y', 'which is bigger'. It distinguishes from sibling tools by noting it replaces 8-15 sequential lookups.

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

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

The description provides explicit when-to-use scenarios (comparison, ranking queries) and mentions that it replaces multiple sequential lookups, implying alternatives. However, it does not explicitly state when not to use this tool vs other siblings.

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

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

The description adds significant behavioral context beyond the annotations (readOnlyHint, idempotentHint): it returns top-N relevant tools with full input schemas and curated examples, ready to call directly. 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 relatively concise for the amount of information, front-loading the core purpose. A few extra details (e.g., list of domains) are useful but could be slightly trimmed without loss.

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 large number of sibling tools and no output schema, the description thoroughly explains what the tool returns (tool names, descriptions, schemas) and when to use it. It provides complete context for effective agent decision-making.

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

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

Schema coverage is 100% and the description only mentions the query parameter and its aliases, adding little new meaning. The baseline of 3 is appropriate given the schema already documents all parameters well.

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

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

The description clearly states the tool finds tools by describing data or task, listing many example domains. It distinguishes itself as a meta-tool for browsing or searching available tools, which sets it apart from siblings.

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

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

The description explicitly advises to call this tool FIRST when many tools are available and you want to see options. While it doesn't explicitly say when not to use it, the guidance is clear and contextually appropriate.

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

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

The annotations already indicate readOnlyHint: true, openWorldHint: true, idempotentHint: true, destructiveHint: false. The description adds value by detailing return fields, data sources, statuses (patents sunset, soft-fail), and fallbacks (GDELT→GNews). 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 a single paragraph that is informative but somewhat dense. It could be slightly more concise or structured (e.g., bullet points) for easier parsing. However, every sentence adds value, and there is no redundancy.

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

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

Given the tool's complexity (multiple data sources) and the absence of an output schema, the description is thorough. It explains return values, data sources, limitations (patents deactivated), and fallback mechanisms. An AI agent can understand what the tool does and 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 description coverage is 100% with both parameters described. The description adds meaning beyond the schema: for 'type' it clarifies only 'company' supported, and for 'value' it specifies ticker or zero-padded CIK and warns that names are not supported. This additional context is helpful but not essential given the schema already covers the basics.

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: 'Get everything about a US public company in one call.' It specifies the verb 'get' and the resource 'everything about a US public company,' and differentiates from sibling tools by mentioning it consolidates multiple pack tools (SEC EDGAR, XBRL, USPTO, news, GLEIF). This is specific and unambiguous.

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

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

The description explicitly states when to use the tool: 'Use when a user asks "tell me about X", "research Acme", "brief me on Tesla", or you'd otherwise call 10+ pack tools.' It also provides guidance on what not to use: 'Names not supported (use resolve_entity first).' This gives clear context and alternatives.

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

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

Annotations already indicate destructiveHint true and idempotentHint true, which the description aligns with by stating 'Delete.' However, the description does not add extra details like error behavior or confirmation requirements, but it is consistent and adequate.

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

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

Two short, focused sentences: first states purpose, second provides usage guidance. No redundant words; every sentence adds value.

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

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

For a simple delete operation with one parameter, the description is complete. It covers purpose, usage conditions, and relationships to sibling tools. No output schema needed; annotations cover safety.

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

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

The single 'key' parameter is well-documented in the input schema (100% coverage). The description repeats 'by key' but does not add new semantic detail beyond the schema property description.

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

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

Description clearly states 'Delete a previously stored memory by key' with a specific verb and resource. It distinguishes from siblings 'remember' (store) and 'recall' (retrieve), making purpose unambiguous.

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

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

Explicitly states when to use: 'when context is stale, task is done, or you want to clear sensitive data.' Also suggests pairing with 'remember' and 'recall', providing clear guidance on tool 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 indicate read-only, idempotent, non-destructive, and open-world. The description adds behavioral details like fetching the page, extracting content, and emitting standard markdown, which augments the annotations without contradiction.

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

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

The description is a single, well-organized paragraph that starts with the main action, then details the steps, and ends with use cases. No extraneous information, every sentence serves a purpose.

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

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

Given no output schema, the description adequately explains the output format (single text blob for site-root) and what is extracted. It could mention edge cases like error handling, but for a straightforward tool with good annotations, it is sufficiently 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?

Both parameters have descriptions in the input schema (100% coverage). The description hints at 'max_links' through 'key links' but does not add significant new meaning beyond what the schema provides, making baseline score 3 appropriate.

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

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

The description clearly states it generates an llms.txt file by fetching a URL, extracting metadata, and outputting standard markdown. It also lists specific use cases, distinguishing it from any sibling tools that do not perform llms.txt generation.

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

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

The description provides explicit use cases (client indexing, own project, competitor auditing) but does not mention when not to use or alternatives. However, given the lack of directly related sibling tools, the context is clear enough.

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

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

Annotations already declare readOnlyHint=true, so the description adds marginal value by listing returned fields but does not reveal significant new behavioral traits beyond what annotations convey.

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. Front-loaded with the core action and immediately followed by key return fields and usage context.

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

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

Given the tool's simplicity, good annotations, and complete schema, the description adequately covers purpose, return fields, and usage timing. No output schema, but enumerated return fields suffice.

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 a clear description of the 'id' parameter. The description reiterates 'by its item id' but adds no new semantics beyond what the schema provides.

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

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

The description clearly states it gets full metadata for a single OneDrive file or folder by item id, distinguishing it from siblings like onedrive_list_files or onedrive_get_file_content.

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

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

Explicitly advises use after listing or searching to inspect one document, providing clear context. Lacks explicit alternatives but sufficiently implies sibling tools for other use cases.

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

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

Beyond the annotations (readOnlyHint, destructiveHint false), the description discloses critical behavioral details: content cap of ~100,000 characters with truncation flag, and the outcome for binary files. This fully informs the agent about limitations and expected behavior.

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

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

The description is two sentences: the first states the core action and resource, the second provides usage boundaries and caveats. Every sentence adds value and no extraneous information.

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

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

Given the single parameter and no output schema, the description covers the key aspects: what it does, file-type suitability, content cap, and truncation signal. It could optionally mention that content is returned as a string, but the lack of output schema makes this less critical. Still, it is largely 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 schema already has 100% coverage with a description for the 'id' parameter. The description adds no new parameter-specific information beyond confirming that the ID is a 'drive-item id', which is marginally helpful but not essential. 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 starts with a specific verb 'Download and return' and resource 'text content of a OneDrive file by its item id', clearly distinguishing from sibling tools like onedrive_get_file (which may handle binary). It also specifies supported file types, making the purpose highly clear and actionable.

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 it's best for plain-text, Markdown, and CSV files, and warns that binary formats return unreadable bytes. This provides clear guidance on when to use the tool and when to avoid it, though it does not explicitly mention alternatives for binary files.

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 convey readOnlyHint, idempotentHint, and non-destructive behavior. The description adds specific return fields but no additional behavioral traits beyond what annotations provide.

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

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

Two sentences, front-loaded with core purpose. Every sentence adds value, no wasted words.

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

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

For a zero-parameter tool with no output schema, the description lists three specific return items and usage context. It is fully complete given the tool's simplicity.

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

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

There are no parameters, and schema coverage is 100%. The rule states 0 params baseline is 4, and the description does not need to add parameter meaning.

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

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

The description clearly states the tool retrieves the user's OneDrive profile, listing specific return fields (drive type, storage quota in bytes, owner display name). It distinguishes from sibling tools that deal with files or 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 says 'Use to report storage usage or confirm the connected account,' providing clear context. No exclusions are needed given the simple nature of the 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 indicate read-only, idempotent, non-destructive. Description adds return fields (id, name, size, is_folder, last-modified, web URL) and implies pagination with top parameter. Sufficient additional context.

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

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

Three sentences, no redundancy. Purpose, usage, and return values are front-loaded. Highly efficient.

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

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

For a simple list tool with no output schema, the description adequately explains return fields and parameter usage. Some behavioral details (e.g., pagination limits) are in schema, not description, but overall complete.

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

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

Schema coverage is 100% with descriptions for both parameters. Description adds example paths ('Documents/Reports') but does not significantly enhance meaning beyond the schema. 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 files and folders in a OneDrive folder, with specific instruction on path usage (relative to root or root). It differentiates from sibling tools like onedrive_search_files by indicating it is for browsing.

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 (browse documents) and path instructions. No explicit when-not-to-use or alternatives among siblings, but the scope is well-defined.

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

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

Annotations already indicate read-only and idempotent. The description adds that it returns name, web URL, and who shared it, providing useful return structure context beyond annotations.

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

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

Two sentences, each earning its place: first describing action/scope, second describing output and usage. No wasted words.

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

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

For a simple read-only list tool with one optional parameter and no output schema, the description provides all necessary context: what it does, what it returns, and when to use.

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

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

Schema coverage is 100% with the 'top' parameter well-described. Description adds no additional parameter semantics, so baseline score of 3 applies.

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

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

The description clearly states it lists files and folders shared with the user, specifically called 'Shared with me'. This distinguishes it from sibling tools like onedrive_list_files (own files) and onedrive_search_files (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 says 'Use to find documents shared by colleagues', giving a clear use case. It does not explicitly exclude alternatives but implies when to use.

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

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

Annotations already provide readOnlyHint and destructiveHint=false, so the description adds value by explaining that search extends to file content and returns specific fields. No contradiction, but it doesn't delve into rate limits or auth nuances.

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 action, and every word adds value. No unnecessary 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?

Given the low complexity, well-covered schema, and safety annotations, the description is complete. It explains what the tool searches, returns, and when to use it.

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

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

Schema coverage is 100%, and the description merely restates the parameter descriptions from the schema without adding new meaning or context. Baseline score of 3 is appropriate.

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

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

The description clearly states the tool's purpose: search a user's OneDrive for files/folders by query across names and content. It specifies return fields, distinguishing it from sibling tools like onedrive_list_files which list without 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 says 'Use to find documents by keyword,' which is clear guidance. However, it does not explicitly contrast with alternatives or state when not to use, leaving some room for ambiguity.

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

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

Annotations are minimal but non-contradictory. Description adds key behavioral info: rate-limited to 5 per identifier per day, free, not counted against tool-call quota. This goes beyond annotations to inform the agent of operational constraints.

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. Each sentence adds value: purpose, usage scenarios, behavioral constraints, and formatting guidelines. No wasted words. Front-loaded with the primary action.

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

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

Given the tool's simplicity (no output schema, straightforward parameters), the description fully covers what an agent needs: what it does, when to use, rate limits, and formatting rules. Complete for its 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 covers 100% of parameters with descriptions. The description adds context about how to frame feedback (e.g., 'describe the issue in terms of Pipeworx tools/packs'), but this is minimal added value beyond schema. Baseline 3 is appropriate.

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

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

Description clearly states the tool is for providing feedback about bugs, features, data gaps, or praise. It explicitly lists the categories and distinguishes the tool by being a communication channel to the Pipeworx team. No sibling tool overlaps with this 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 tells when to use: for bugs, missing features, data gaps, or praise. Also provides negative guidance: 'don't paste the end-user's prompt'. Mentions rate limits and quota-free nature, helping agent decide when to invoke.

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

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

Annotations already indicate read-only and idempotent behavior. The description adds valuable details about data source (CF analytics-engine), privacy (no PII), and caching (5min-1h), exceeding what annotations provide.

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

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

The description is structured with bullet points and front-loaded information. It is slightly wordy but every sentence adds value; minor tightening possible.

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

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

Given the tool's simplicity (one optional parameter, no output schema), the description covers all necessary aspects: return value, use cases, data source, caching, and privacy. No gaps remain.

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

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

The only parameter 'window' is fully described in the schema with enum values. The description adds context on how window choice affects results (hot vs steady-state), enhancing understanding beyond the schema.

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

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

The description clearly states the tool returns top tools, top packs, and total call volume over a window. It uses specific verbs and resource description, distinguishing it from sibling tools like discover_tools.

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

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

Three specific use cases are listed, providing clear guidance on when to use the tool. However, it does not explicitly exclude scenarios or mention alternatives, which would earn a 5.

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

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds significant behavioral detail: how it walks child markets, checks ordering, computes partition checks, applies similarity thresholds, and filters placeholders. 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 paragraph but effectively organized with clear sections for each mode, constraints, and response format. It is front-loaded with the core purpose and then details. While comprehensive, it could be slightly more concise.

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

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

Given no output schema, the description fully explains the response structure: opportunities array with fields and the partition_check object. It covers all input parameters, modes, constraints, and response details, making it self-contained for an agent to correctly invoke the tool.

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

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

With 100% schema coverage, the schema already defines the two parameters. The description adds value by explaining the parameters' roles in each mode (e.g., 'event' can be a slug or URL, 'topic' is a seed question for cross-event search) and providing examples, going beyond the schema.

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

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

The description clearly states the tool finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It specifies two modes ('event' and 'topic') with distinct behaviors and examples, differentiating it from siblings like 'polymarket_edges'.

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

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

The description explicitly outlines when to use each mode with concrete examples (e.g., 'event' for a single slug, 'topic' for a seed question). It also provides constraints like Jaccard similarity threshold and partition filtering, giving clear usage context. However, it lacks explicit '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 goes far beyond annotations by detailing three model families, edge components, market move warnings, tradeable-edge knobs, caching (1h), and diagnostics to explain empty segments. It fully discloses behavioral traits.

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 clear sections (segments, edge components, knobs). Every sentence adds value, though some brevity could be gained without losing clarity.

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

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

Despite no output schema, the description fully explains the response structure (by_segment, fed_candidates, diagnostics) and caching behavior. It provides all necessary context for correct invocation and understanding.

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: explains min_kelly applies only to single-leg, min_partition_leg_kelly for partition per-leg, and provides context for defaults and usage of all 9 parameters.

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

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

The description clearly states the tool scans top Polymarket markets and returns opportunities where Pipeworx data disagrees with market price. It uses a specific verb ('scan and return') and resource ('opportunities'), and the detailed segments distinguish it from siblings like polymarket_arbitrage.

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

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

The description explicitly frames usage as 'what should I bet on today' and explains knobs and caching. However, it does not provide explicit when-not-to-use guidance or direct comparison to sibling tools, though the detailed segments imply usage 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 declare readOnlyHint, idempotentHint, etc. The description adds substantial behavioral context: response structure with safety fields (compatibility_warning, temporal_alignment, skipped_cross_type), conditions when spreads are meaningful, and how skipped comparisons are exposed. No contradiction with annotations.

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

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

The description is dense but well-organized, starting with core purpose, then modes, response fields, and safety warnings. Each sentence adds value; minor verbosity could be trimmed but overall efficient.

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

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

Given no output schema, the description adequately explains response components (leg-by-leg prices, matched spread, safety fields). It covers temporal alignment, compatibility warnings, and skipped cross types. Missing explicit JSON structure, but sufficient for agent understanding.

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%, but the description adds value by listing all 10 topic shortcuts and explaining that explicit parameters override topic mapping. This goes beyond what the schema provides.

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

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

The description clearly states the tool computes the cross-venue spread between Kalshi and Polymarket for the same resolving question, with specific verb ('spread') and resource. It distinguishes from siblings by being the only tool dedicated to cross-venue comparison.

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

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

Explains two modes (topic shortcuts vs explicit tickers) with examples and explicitly warns that most pre-mapped topics may not be tradeable due to compatibility warnings. Provides 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. The description adds scoping (anonymous IP, BYO key hash, account ID) and behavior when key is omitted (list all keys). It does not cover error handling but annotations reduce the burden.

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

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

The description is three sentences, front-loaded with the main action, and each sentence adds distinct value (function, use case, scoping, pairing). No filler.

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

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

Given the tool's simplicity (one optional param, no output schema, rich annotations), the description covers all essential aspects: function, use case, scoping, and sibling relationships. It is complete.

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

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

Schema coverage is 100% with a clear description of the key parameter. The description reinforces the same meaning ('omit to list all keys') but adds no additional semantic 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 retrieves a previously saved value or lists all keys when key is omitted. It provides concrete examples (ticker, address, research notes) and distinguishes from siblings remember and forget.

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

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

The description explicitly says when to use (to look up stored context) and pairs with remember and forget, implying alternatives. It does not give explicit 'when not to use' but the guidance is sufficient.

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

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds valuable behavioral details: parallel fan-out to multiple sources, fallback from GDELT to GNews, soft-fail for USPTO patents, and return structure. 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 reasonably concise for the complexity, but could benefit from bullet points or shorter sentences for readability. It front-loads the purpose effectively.

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 with multiple data sources and parameters, the description covers all essential aspects: sources, fallback behavior, input formats, return structure (grouped changes, count, citation URIs), and distinguishes from sibling 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 parameter descriptions. The description enriches semantics by explaining `since` format (ISO or relative shorthand), providing examples and recommended values, and clarifying `type` limitation to 'company' only.

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

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

The description clearly states the tool returns recent changes for a company from SEC, news, and patents within a time window. It provides example queries like 'what's happening with X' and explicitly distinguishes from sibling tool entity_profile by specifying when to use each.

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 use cases and a direct alternative (entity_profile for static profile). However, it does not explicitly state when not to use this tool (e.g., if only static data needed), but the context implies 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 adds context beyond annotations: key-value pairs scoped by identifier, memory retention duration (24 hours for anonymous), and that it is not read-only or destructive. Annotations confirm idempotentHint=true and 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 front-loaded with the main purpose and is well-structured, but it could be slightly more concise. Some phrases like 'across this conversation or across sessions' could be merged, but overall it is efficient for the information provided.

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 storage semantics, scoping, and retention. It covers key aspects needed for an agent to use the tool correctly, though it could mention the return value (likely the stored value or success confirmation).

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by providing concrete examples for key (e.g., 'subject_property') and value ('any text'), helping agents understand usage beyond the schema's abstract descriptions.

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

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

The description uses specific verbs like 'Save data' and 'reuse later', and distinguishes itself from siblings 'recall' and 'forget' by naming them explicitly. It clearly states what the tool does and its scope.

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

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

The description provides explicit guidance on when to use the tool ('discover something worth carrying forward') and pairs it with 'recall' and 'forget' for retrieval and deletion. It also notes the persistence difference between authenticated vs anonymous sessions.

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 and idempotentHint. The description adds behavioral context: it cascades through several lookup endpoints internally, replaces multiple manual lookups, and details the output format for each type (e.g., ticker, CIK, citation URI for companies). No contradictions.

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

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

The description is well-structured with a clear first sentence stating the purpose, followed by detailed type-specific output. It is concise and front-loaded, though slightly verbose in describing the cascading behavior.

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 return values for both entity types (ticker, CIK, company_name, citation for company; RxCUI, ingredient, brand, citation for drug). It covers input acceptance and auto-disambiguation, making it complete for the tool's complexity.

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

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

Input schema has 100% coverage with descriptions for both parameters. The description adds value by providing examples (AAPL, 0000320193, ozempic) and noting auto-disambiguation for company names, which goes beyond the schema.

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

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

The description clearly states it resolves user-spoken names to canonical identifiers needed by other tools, with specific examples for company and drug types. It distinguishes from siblings by noting it replaces 2-3 manual lookups and is the first step when you have a name but need an ID.

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 when you have a name but need an ID,' providing clear usage context. It does not explicitly state when not to use it or compare to sibling tools, but the direct guidance is strong and sufficient.

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

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds value by detailing the probing mechanism (using ai_visibility_check), the ranking process, and the output structure (score, confidence, signal density). No contradictions exist.

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

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

The description is concise, consisting of three sentences. The first sentence immediately conveys the core purpose. No unnecessary words or repetitions.

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

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

Despite the absence of an output schema, the description adequately explains the return value: a ranked list with score, confidence, and signal density. It covers input constraints, use case, and behavior, making the tool fully understandable.

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

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

Schema coverage is 100% with all parameters described in the schema. The description adds modest context—e.g., the 'entities' first entry is the subject—but mostly confirms what the schema already states. Baseline 3 is appropriate given full schema coverage.

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

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

The description clearly states the tool compares AI visibility across multiple entities side-by-side, probing each with ai_visibility_check and ranking results. It distinguishes itself from sibling tools like ai_visibility_check, which is for single entities, by emphasizing the comparative, multi-entity aspect.

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

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

The description provides a concrete use case ('competitive AI-marketing audits') and an example question ('does Claude know about us as well as our competitors?'). However, it does not explicitly state when not to use the tool or mention alternative tools like compare_entities, though the sibling context makes the comparison to ai_visibility_check clear.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable context: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30s, and sources_failed lists timeouts. This goes beyond annotations without contradiction.

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

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

The description is concise but dense, covering purpose, usage, behavior, and limitations in a single paragraph. It is front-loaded with the main purpose. However, it could be slightly more structured (e.g., bullet points for output fields), but overall it 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?

Given no output schema, the description fully explains the return value structure (summary block, per-advisory detail, links, alternative versions). It also covers edge cases (scoped packages, version default), failure behavior, ecosystem constraints, and alternatives, making it complete for the tool's complexity.

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

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

Schema coverage is 100% (both parameters described), so baseline is 3. The description adds extra semantics: scoped packages are accepted ('@types/node'), and version defaults to latest when omitted. 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's purpose: a composite check for adding an npm package, combining multiple data sources. It uses a specific verb ('check') and resource ('npm package'), and distinguishes itself from siblings like 'bet_research' or 'scan_competitor_ai_presence' by focusing on npm dependencies.

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 describes when to use: 'whenever an agent asks is X safe / popular / small or what does adding lodash cost me'. Also specifies limitations: 'NPM ecosystem only in v1' and directs other ecosystems to deps.dev:version directly. This provides clear guidance on when to avoid this tool.

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

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

Disclosure goes well beyond annotations: it explains the return structure (verdict, structured form, actual value with citation, percent delta). No contradictions with readOnlyHint, openWorldHint, 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?

Concise yet comprehensive: purpose, usage, scope, and output are covered in three sentences. No redundancy; every sentence adds value.

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

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

Given the single parameter, clear annotations, and detailed output description (despite no output schema), the tool is fully specified for an agent to use correctly.

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

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

The single parameter 'claim' is fully described in the schema (100% coverage). The description adds examples and clarifies the natural-language nature, reinforcing 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 specific verbs ('fact-check, verify, validate, confirm/refute') and clearly states the resource ('natural-language factual claim against authoritative sources'). It distinguishes itself from sibling tools by noting it replaces 4–6 sequential calls.

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

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

Explicitly describes when to use ('when an agent needs to check whether something a user said is true') with concrete examples. Also states the scope (company-financial claims for public US companies) and lists out-of-scope items implicitly via the scope limitation.

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