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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful behavior beyond that: it bounds scope (no source code, files, or URLs) and discloses the failure mode ("Unknown ids fail"), which an agent needs for error handling.

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?

Purpose is front-loaded in the first clause and every sentence carries information about scope or capability. It is slightly cluttered by the two consecutive skills clauses and parenthetical examples, which reduce scanability without being wasteful.

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 read-only doc-fetch tool with no output schema, the description covers what is retrievable (contracts, signatures, behavior notes, skills craft), where valid ids come from, and what is out of scope. Nothing material an agent needs before calling 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 both `id` and `projectId` are already fully documented, including the skills-prefixed examples and the null/omitted behavior for projectId. The description's parameter content largely restates the schema, adding little beyond 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 (read) plus resource (one API reference/guide page) and enumerates the content types returned: signatures, argument order, layout/text behavior, animation and SkSL shader contracts. It also pinpoints where ids come from (search_docs) and notes the secondary skills path, so an agent can separate it from search_docs without opening the schema. The only soft spot is the unaddressed relationship to the load_skill sibling for the skills path.

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?

Gives a clear entry condition (an id from search_docs, a node/symbol name, or a guide name) and explicit negative scope: no implementation source, no arbitrary files or URLs. It does not, however, tell the agent when to pick this over load_skill for reading skills content, so the alternative routing is incomplete.

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