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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering safety. The description adds the behavioral nuance that this is not a live fetch (data comes from the index) and discloses the response condition 'If ok is false, the index has no passage', which is useful beyond annotations.

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 short sentences with no filler: purpose, usage, and a key behavioral note. The most important information is front-loaded, and every sentence earns its place without redundancy.

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?

Given no output schema, the description mentions the 'ok' field and the absence condition, which is helpful. It doesn't describe the full passage structure or behavior when both id and source+doc are provided, but the simplicity of the tool and clear parameter guidance make it sufficiently complete for most calls.

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 coverage is 100%, so each parameter is documented individually. The description adds the grouping semantics: id is an alternative to source+doc, clarifying the relationship. This goes beyond the schema's individual descriptions, enhancing the agent's understanding of parameter combinations.

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 returns a stored index passage for a search cite, using the specific verb 'return' and the resource 'stored index passage'. This distinguishes it from sibling tools like search or verify_claim, none of which directly retrieve a stored passage.

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?

It specifies the parameter selection ('Pass id from the cite, or source plus doc') and explicitly notes it is not a live web fetch, which sets an exclusion. However, it doesn't name an alternative tool for live fetching or explain when to prefer this over search, though the context is clear enough for an agent.

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