docs-mcp

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

With no annotations, the description fully discloses key behavior: returns url and markdown content, orders by relevance, and explains that platform filtering occurs post-retrieval and can drastically reduce results. This goes well beyond basic tool intent and informs agent expectations.

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

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

The description is front-loaded with the core purpose, then efficiently adds return format, usage, and a critical caveat. Every sentence contributes, and despite length, it remains tightly structured without redundancy.

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

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

Given no output schema, the description adequately explains return values (url + markdown content) and ordering. It also covers an important behavioral nuance with platform filtering, making it complete for an agent to effectively 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?

The description adds meaningful semantics for the 'platform' parameter, explaining its post-filter effect and the trade-off of omitting it, which is not fully captured in the schema. The schema already covers 75% of parameters, but the platform nuance is valuable.

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

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

The description clearly states the tool searches the official Redpanda documentation and returns relevant sections, which is a specific verb+resource. It distinguishes from sibling tools like search_api_reference by targeting general Redpanda docs versus API reference 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?

It explicitly says to use this tool for all Redpanda knowledge queries, and provides detailed guidance on when to pass 'platform' versus omit it, including a concrete trade-off. This gives clear context on usage and how to adapt based on user deployment.

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?

With no annotations, the description carries the burden of behavioral disclosure. It reveals important constraints: 'Returns up to 10 pages per request' and 'URLs must be from docs.redpanda.com/api/doc/*.' It also sets expectations for the response content without describing error handling or authentication, which prevents a 5.

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 short paragraphs, each earning its place: the first states purpose, the second gives the usage workflow, and the third lists operational constraints. It is front-loaded with the key verb and resource, with 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?

For a two-parameter retrieval tool without an output schema or annotations, the description is nearly complete. It explains what is returned, how to use it, and key constraints. It lacks only edge-case behavior like error handling or rate limits, but the core selection and invocation information 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?

The input schema already covers both parameters thoroughly, including the 'context' parameter rules. The description adds value by specifying the URL domain restriction and reiterating the 10-page limit, which goes beyond the schema's description for 'urls'.

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 opens with 'Retrieve full content of API reference pages by URL' and clearly specifies the return value: 'complete endpoint details including parameters, request/response schemas, and examples.' It distinguishes itself from sibling tools by explaining it consumes URLs from list_api_reference_pages or search_api_reference.

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 workflow guidance: 'Use this after finding pages via list_api_reference_pages or search_api_reference. Pass the URLs from those results directly.' It names the relevant sibling tools and implies the intended sequence, though it does not explicitly state when not to use 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?

No annotations are provided, so the description carries the burden. It states the action ('Check for additional tools') but does not disclose what the tool returns or any side effects. The behavior is fairly self-explanatory for a discovery tool, but the output format is unspecified.

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 sentence, front-loaded with the action, and contains no unnecessary words. It is appropriately sized for the tool's simplicity.

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 explains when to use it but does not mention the return value or any further details. This leaves a moderate gap in understanding the tool's full behavior.

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

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

The schema fully covers the one parameter 'context' with a clear description (100% coverage), so the tool description adds no additional parameter semantics. Baseline 3 applies per the rules.

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

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

The description clearly identifies the action ('Check for additional tools') and specifies the purpose ('whenever your task might benefit from specialized capabilities'). It distinguishes itself from sibling tools that handle API reference queries, like search_api_reference or get_api_reference_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?

It explicitly states when to use the tool ('whenever your task might benefit from specialized capabilities') and even encourages use when existing tools could work ('even if existing tools could work as a fallback'). This provides a clear decision rule for the agent.

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

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

With no annotations, the description carries the behavioral transparency burden. It discloses the return fields and the exact scoping behavior for each api value, including that omitting api lists all. It does not mention pagination, authentication, or error handling, but for a read-only listing tool these are less critical. The scoping details go well beyond a generic statement.

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: a one-sentence summary, a scoping list, and a final usage note. Every sentence earns its place, with no redundancy or filler. The formatting improves scannability.

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

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

For a list tool with no output schema and no annotations, the description provides a complete picture: what it does, what it returns, how to scope it, and when to use an alternative. The parameter semantics are thoroughly covered. Given the tool's simplicity, nothing essential is missing.

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, but the description adds substantial meaning beyond the schema. It elaborates on each api value (admin, cloud-controlplane, etc.) with concrete operation examples, which the schema does not provide. This makes the api parameter far more understandable and actionable.

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

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

Description starts with a clear verb+resource: 'List pages in Redpanda API reference documentation.' It specifies what is returned (endpoints, schemas, topic pages with URL, title, type, description) and distinguishes from siblings by noting 'Use this to browse API structure' and pointing to ask_redpanda_question for general docs.

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 this tool ('to browse API structure') and when not to ('For general Redpanda docs, use ask_redpanda_question instead'). The extensive scoping section gives detailed guidance on parameter values, making it clear how to target different APIs.

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?

With no annotations provided, the description carries the full burden and does well: it discloses the scope of results (up to 20 matches), the return components (URL, title, text excerpts), and the meaning of each api scoping value. However, it does not mention behaviors like no-results handling, ordering, or rate limits, which would strengthen transparency for a search tool.

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

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

The description is structured with clear headers (SCOPING, WHEN TO USE WHICH) and a final pointer to an alternative tool. While it is somewhat lengthy, every section serves a purpose: the scoping lists are essential for correct parameter use, and the examples are directly actionable. There is no filler or repetition.

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

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

The tool has 4 parameters and no output schema, so the description must cover both input semantics and output behavior. It does this thoroughly: it describes the return format, explains all api scoping values, provides usage examples, and explicitly distinguishes from sibling tools. This is a complete, self-contained description for the agent.

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

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

The input schema already describes all parameters, so the baseline is 3. The description adds significant value by explaining the semantic meaning of each api value (admin, cloud-controlplane, etc.) and offering concrete examples of when to use each, which goes beyond the schema's terse 'Scope: all or omit' description. This raises the score above baseline.

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

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

The description clearly specifies a verb ('Search') and a resource (Redpanda API reference documentation), and it distinguishes itself from sibling tools by stating that general Redpanda questions should use ask_redpanda_question instead. It also clarifies that it returns up to 20 matching endpoints, schemas, or topics with URL, title, and excerpts, making its purpose unambiguous.

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

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

The description provides explicit 'WHEN TO USE WHICH' examples mapping user queries to specific api parameter values, and it explicitly directs non-API-specific questions to ask_redpanda_question. This is strong, actionable guidance that helps an agent choose this tool over alternatives and configure it correctly.

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