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

The description goes well beyond the `readOnlyHint: true` annotation by disclosing nuanced behaviors: fuzzy/leaf heading matching, auto-prepending the H2 parent's intro for deep headings, and keyed-catalog behavior where no heading lists top-level keys. It also reveals the 404 response format (available headings + cross-file hints), which is crucial for an agent to recover gracefully.

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 every sentence earns its place, covering primary purpose, retrieval workflow, heading semantics, native/code-symbol alternatives, catalog patterns, and error behavior. It is front-loaded with the core action and progressively adds edge cases, with no fluff or repetition of schema 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?

For a tool with no output schema, the description compensates by covering input semantics, return value expectations (full markdown or section), error recovery (404 hints), and edge cases like keyed catalogs and community paths. Combined with the rich input schema and readOnly annotation, the agent has everything needed to select and 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?

Although schema coverage is 100%, the description adds substantial meaning: it explains the `path` shape (`<category>/<file>.md` vs `learning:<id>`), warns against inventing `learnings/<slug>.md`, and clarifies that `heading` accepts either full breadcrumbs or leaf names, is case-insensitive and fuzzy, and must not be used for code symbols. This transforms bare parameter definitions into actionable guidance.

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 a clear verb and resource: 'Fetch full markdown of a doc by `path`', and specifies exact source tools (`browse`, `semantic_search`, `grep_docs`) that produce valid paths. It also differentiates from siblings by directing users to `lookup_native` for script natives and `grep_docs` for code symbols, making the tool's unique role 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?

Explicit usage guidance is abundant: 'Use to retrieve full content after a search snippet looks promising' establishes the primary trigger, and alternatives are specified for natives (`lookup_native`) and code symbols (`grep_docs`). It even explains how to handle community findings (`learning:N` paths) and discouraged path shapes, leaving no ambiguity about when to invoke this tool.

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