developer-toolkit-mcp

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

The description adds meaningful behavioral context beyond the readOnlyHint and openWorldHint annotations: it discloses that the full text is returned, clarifies that `metadata.gated` only indicates paywall status (not access to the content), and explicitly warns that an unknown id produces an error. These details help the agent predict behavior and act accordingly.

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 compact and every sentence earns its place: purpose, retrieval source, example, return-behavior note, and error guidance are all packed into three sentences. It is front-loaded with the core action and resource, making it immediately scannable.

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

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

Given the single required parameter, the presence of an output schema, and the read-only annotation, the description covers all essential aspects: what the tool returns, how to obtain a valid input, what error to expect, and the meaning of a potentially confusing field. Nothing critical is missing for an agent to invoke this tool correctly.

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

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

The schema already fully describes `id` as 'Article id from a `search` result', so the parameter is well documented. The description reinforces this by restating the source of the id and adding a concrete example, which helps an agent form a correct mental model without adding substantial new semantics.

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 specific action ('Retrieve the complete markdown of one documentation article') and clearly identifies the resource and key by which it is retrieved (the id returned from `search`). It also gives a concrete example id, making the purpose unambiguous and distinguishing it from its sibling `search`, which finds articles rather than fetching one.

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 instructs the agent to call `search` first, states that the id comes from `search`, and warns that an unknown id is an error. This effectively tells the agent when to use this tool and when to use the sibling `search` instead, leaving no ambiguity about the correct sequencing.

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 and openWorldHint=false. The description adds concrete behavioral details beyond those: at most 10 ranked results, snippets rather than full article text, empty-list semantics, and language-dependent result behavior. It thoroughly explains what the agent should expect from the call.

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 dense sentences, all information-bearing. The core action is front-loaded, followed by behavioral limits and the integration with the sibling tool. No filler or 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?

For a single-parameter, read-only search tool with an output schema present, the description covers corpus scope, result limit, snippet output, no-result behavior, and the next step (`fetch`). Nothing essential is missing for an agent to call it correctly.

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

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

Schema description coverage is 100%, with the `query` parameter fully documented as a natural-language string. The description's mention that Polish queries return Polish articles repeats the schema and adds no new meaning. Baseline 3 is appropriate because the schema already does the heavy lifting.

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?

States a specific verb and resource: 'Search the AI Developer Toolkit documentation', and enumerates the corpus scope (950+ guides, specific tools, topics, languages). It also distinguishes the tool from its sibling `fetch` by describing the snippet-based output and pointing to `fetch` for full text.

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 outlines the search-to-fetch workflow: search returns ranked snippets, then 'Pass a result id to `fetch` for the full text.' It sets clear expectations for an empty result list. It does not explicitly say when not to use search, but with only one sibling the intended usage is clear enough.

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