Bolt Claw documentation

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the response is the full page rendered as markdown, not a snippet or summary. It omits any mention of size limits, truncation, or error behavior for a non-existent id.

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

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

Two short sentences, zero waste, with the core action and return format front-loaded before the id convention. Every clause carries information the agent needs to call the tool correctly.

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 one-parameter read tool with annotations and no output schema, the description covers what it returns (full page as markdown) and how to form the id, which is most of what is needed. Error handling for invalid ids and any page-size limits are the only meaningful omissions.

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 the schema already defines and exemplifies `id`, setting the baseline at 3. The description adds the derivation rule ('the page's path without /docs/'), which is real meaning beyond the schema, but it stops short of edge-case syntax guidance, so it does not clearly exceed the 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?

States a specific verb and resource ('Read one documentation page in full, as markdown') and implicitly separates itself from the `search` sibling by tying the `id` input to search results. An agent knows immediately this retrieves a single page rather than discovering pages.

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 establishes the workflow precondition: the id comes from `search`, so the agent knows to call search first when it lacks an id. It does not explicitly state when not to use this tool or what to do if the id is unknown, leaving a small gap.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds genuine value by disclosing the result shape (id, title, URL, matching line) and ordering ('best first'). It does not explain how relevance is ranked or what an empty result set looks like, which are the remaining gaps.

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 short sentences, front-loaded with the purpose, then the return contract, then the next-step handoff. No filler, and every sentence carries information the agent needs.

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

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

With no output schema, the description correctly compensates by naming the returned fields and their order, which is what an agent needs to chain into `fetch`. Minor omissions remain: no mention of no-match behavior or total-result awareness, but for a two-parameter read tool this is close to 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 both `query` and `limit` fully documented including default and maximum, so the baseline of 3 applies. The description adds no meaning beyond the schema — it says nothing about query syntax, phrase handling, or how `limit` interacts with ranking.

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 ('Find documentation pages about a subject') and immediately distinguishes itself from its sibling by noting the id is passed to `fetch` to read a page. An agent can tell search vs. fetch apart without opening either schema.

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 closing sentence gives an explicit workflow handoff — use `search` to locate, then `fetch` with the returned id — which effectively routes the agent to the sibling. It stops short of stating when NOT to use this tool (e.g., when you already have a page id, go straight to `fetch`), so it is clear context without explicit exclusions.

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