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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds useful behavioral context beyond these annotations: it explains what each mode returns (compact field digest vs. full page including Examples/SDK snippets) and specifies the accepted pathname patterns. It does not describe error handling or auth requirements, but the readOnly annotation already covers the safety profile and the description provides meaningful mode semantics.

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 sentences, each carrying essential information: the action and source, the mode behavior, and the accepted pathname formats. No filler or redundant restatement of the tool name.

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?

Despite having no output schema, the description gives an adequate sense of the return format for both modes (compact field digest vs. full page with Examples). It clearly ties the required docsPathname to docs_search, documents mode variants, and the schema covers the remaining required params (context, llm_model) with precise instructions. An agent has enough to invoke the 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?

Schema description coverage is 100%, so the schema already documents all five parameters thoroughly. The description adds minor value by explicitly tying docsPathname to docs_search and noting acceptable pathname prefixes, but this largely echoes the schema's own examples and the mode param description. Baseline 3 is appropriate.

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's function: read a corpus page using a docsPathname obtained from docs_search. It distinguishes itself from the sibling docs_search tool by specifying the read action, the accepted pathname families, and the mode options, leaving no ambiguity about what it does.

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 explains when to use the tool (after obtaining a pathname from docs_search) and provides specific guidance on choosing mode=outline versus mode=full for different content needs. It references docs_search as the source of the pathname, which implicitly guides the agent away from using docs_read without a prior search, though it doesn't explicitly state 'use docs_search when you don't have a pathname'.

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