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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds real value beyond them: it explains the response varies by state (status now, result when complete, retry delay while queued/running), which tells the agent how to poll.

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?

One front-loaded sentence with no filler; every clause (status, result, retry delay) conveys distinct information the agent needs to use the tool correctly.

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?

An output schema exists, so return values need not be spelled out, and the description still explains how the response differs across job states. The only real gap is anything about error conditions for an invalid or expired operationId.

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 burden for operationId. It implies the parameter must reference a previously started operation, but never states the 'op_' format, where the ID comes from, or what happens on an unknown/expired ID.

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 (checks an operation, returns status/result/retry delay) and scopes it to 'previously started' operations, which separates it from list_operations. It does not name a sibling explicitly, so it falls just short of the top mark.

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?

'Previously started' and 'while work is queued or running' make the polling use case clear, and the retry delay hints at the intended loop. There is no explicit when-not guidance or named alternative (e.g. list_operations for enumerating all jobs).

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