get_result

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

Beyond readOnlyHint=true, it discloses cost behavior (free, never charges, no new data call), retention policy (results deleted 30 days after the call), and the error shape for expired results. It also notes the token is secret and the result is withheld without it — exactly the context annotations cannot carry.

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?

Front-loads the two most decision-relevant facts (free, read-only) and each sentence carries distinct information. There is mild redundancy between 'FREE', 'instead of paying again', and 'Retrieval never charges', which keeps it from a 5.

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 no output schema and full param coverage, the description covers what is returned (stored result or status like completed/failed), the expiry edge case, and the auth requirement. It does not describe behavior for an invalid/mismatched request_id or token, leaving one gap for a lookup tool with error paths.

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 already 100%, and the description adds provenance meaning: both values come from the original paid response and the result_token is a ~32-char secret required to view the result. It does not add format/syntax detail beyond what the schema states, so 4 rather than 5.

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?

States a specific verb and resource: fetch the stored result (or status) of a paid call, identified by request_id and result_token. It carves out a distinct niche in the family (retrieving an already-computed answer rather than re-running a call), though it never names the sibling retry_request that an agent would otherwise consider.

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?

Gives a clear trigger: 'Use it instead of paying again when an answer was lost,' plus the note that retrieval never charges and never triggers a new data call. It does not explicitly state when not to use it or name retry_request as the alternative for genuinely failed/never-computed requests.

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