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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the safety profile is covered. The description adds nothing beyond restating the endpoint—no polling cadence, no meaning of the progress payload, no indication of what a jobId refers to.

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 endpoint path is duplicated verbatim in the first two sentences, which wastes space without adding information. The operation ID and describe_operation note are the only non-redundant content.

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?

There is no output schema, so the description would need to explain what 'progress' returns (percentage, state, errors) but does not. Combined with undocumented parameters and no sibling differentiation, the definition is too thin for reliable invocation.

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 should compensate for the two parameters (required jobId, optional query), but it says nothing about them. An agent learns only from the parameter names in the schema, not from the description.

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 repeated path 'GET /api/ai/extract/progress/:jobId' does convey the resource (extraction progress for a job) and a read verb, so an agent can infer a polling-status concept. However, it offers no differentiation from closely named siblings like get_ai_extract_status_by_jobId and get_ai_extract_result_by_jobId, leaving ambiguity about which progress/status/result endpoint to pick.

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?

There is no statement of when to use this versus the status or result siblings, nor any precondition. The only hint is that describe_operation can supply native request schemas, which is a plumbing pointer rather than usage guidance.

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