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

Annotations already flag destructive=true, idempotent=true and openWorld=true, but the description adds the material facts an agent actually needs: real credits are charged, the price is locked to the job's snapshot, and a fresh idempotency_key can trigger a second charge. That duplicate-charge warning is genuine behavioral disclosure beyond the structured hints.

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 tight sentences with no filler: the charge/enqueue action leads, the idempotency contract follows, and the double-charge warning closes. Every sentence carries distinct operational information.

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 money-moving mutation with no output schema, the description covers the charge risk, the price-snapshot semantics, and the retry protocol, which are the failure modes that matter most. It does not say what the continuation enqueues or what the call returns, a minor gap given there is no output schema to carry that.

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% across four required parameters, so the description carries the burden. It meaningfully explains idempotency_key (UUID, save it, reuse it on retry) and implicitly explains expected_credits via the 'confirmed credits at the job price snapshot' model, but count and job_no receive no explanation at all.

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 states a concrete action: charge confirmed credits at the stored price snapshot and enqueue a continuation of an export job. That is a specific verb+resource, not a tautology of the name 'resume_export_job'. It never distinguishes itself from siblings like create_export_jobs or quote_export_jobs, so an agent must infer when resumption applies versus a fresh create.

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?

Strong guidance is given for the retry case: reuse the same idempotency_key and arguments to recover the original execution, and a new key may charge again. However, there is no statement of when to call resume_export_job at all, nor how it differs from create_export_jobs, so alternative selection is left to inference.

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