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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context: 'Select a section and continue using the returned offset when text is truncated' explains pagination and truncation handling. This goes beyond annotations and clarifies the tool's operational behavior.

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 two well-structured sentences: the first delivers the core purpose and the second addresses truncation and continuation. There is no redundancy or filler; every phrase serves a purpose. The key action and resource are front-loaded for quick comprehension.

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?

The description covers the primary function and pagination behavior, which is the most critical context. However, with five parameters and no output schema, it omits details like the generation parameter's role and the distinction between section values (all/body/transcript). It is adequate for basic invocation but leaves gaps that could confuse an agent in edge cases.

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 0%, so the description carries the full responsibility for explaining parameters. It explicitly references 'by stable ID' for the id parameter, 'Select a section' for section, and 'continue using the returned offset' for offset and truncation. However, it does not explain the generation parameter, nor the exact semantics of max_chars, and it only hints at section values. Given five parameters, this partial coverage is insufficient for an agent to use the tool optimally.

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 verb 'Read' and the resource: 'original evidence or a labelled Roboto editorial answer and its citations by stable ID.' It also mentions section selection and offset for truncation, giving a precise understanding of the tool's function. This distinguishes it from siblings like search_evidence, which implies searching rather than direct retrieval.

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 implies usage when you have a stable ID, but it does not explicitly state when to use alternatives like search_evidence or get_entity. There is no mention of conditions under which this tool should be avoided or other tools preferred. The guidance is implicit but not explicit enough to fully route an agent.

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