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

Beyond the readOnly/idempotent/destructive annotations, the description discloses the two id modes, the 60,000-character truncation behavior with truncated: true and next pointing to read, and the passage-with-context semantics. It also details the metadata contents, including the citable publisher URL and cited_by count, adding substantial behavioral context.

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 front-loaded with the core purpose and then moves logically from input types to return fields to next steps. It is dense but every sentence earns its place; there is no filler, tautology, or superfluous repetition.

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 one parameter, no output schema, and five siblings, the description covers what to pass, what comes back, when truncation occurs, how to continue, and which sibling to use next. There is no material gap an agent would need to resolve elsewhere.

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?

The schema only defines id as a string with zero description coverage, but the description explains that id may be a passage id from search results or a document id, and specifies the behavior for each. This fully compensates for the schema's silence and removes ambiguity about what value to pass.

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 states a specific verb and resource: 'Read one document, or one passage in its context, by the id search, documents or citations gave.' It also distinguishes itself from siblings by naming read as the continuation for more pages or articles and citations for what a document applies to or is changed by. An agent can immediately identify this as the single-item reader tool.

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 explicitly conditions use on possessing an id produced by search, documents, or citations, which tells the agent when fetch is the right call after those tools. It also routes onward: use read for more pages or one article, and citations for what the document applies to and what changed it. This gives clear start and follow-up context.

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