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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so safety is covered; the description still adds two things the annotations cannot: zero credit cost and the ownership scoping rule ('only the authenticated user's own results resolve; any other id is not found'). The 'Read-only' clause is redundant with annotations but the cost and auth facts are substantive.

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, front-loaded with the action and return contents, then cost/safety, then the routing condition. Every sentence carries distinct information; nothing is padding.

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 single-parameter retrieval tool with an output schema and full annotation coverage, the description supplies the remaining unknowns: what comes back, what it costs, who can read what, and when to prefer it. An agent can call it correctly and interpret the failure case.

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 0% – the saved_id pattern constraint is undocumented in the schema. The description compensates by explaining the id's semantics: it must be one of the caller's own saved results and foreign ids resolve as not found, which is the key behavior an agent needs to interpret a lookup failure.

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?

Specific verb (Retrieve) plus resource (one saved result in full) with a parenthetical enumerating the payload contents. The word 'one' and the scope 'in full' cleanly separate it from list_saved_research and save_research without requiring the schema.

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 when-to-use trigger: 'when the user wants to reuse, re-read or build on something they saved earlier instead of paying to run the tool again.' That contrast with re-running a paid tool is a genuine alternative-routing signal, though no sibling (e.g. list_saved_research) is named for the discovery case.

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