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

Beyond the annotations (readOnly=false, destructive=true, idempotent=false), the description discloses meaningful behavior: it reserves estimated credits and settles actual usage, reuses active runs, produces proposals without applying them, and requires specific permissions. It also clarifies that humanApproved must attest to genuine human approval, which is critical semantic context.

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 description is dense but efficiently structured, leading with the primary mission and then layering constraints, side effects, and permission requirements. Every sentence adds unique value, with no filler or redundancy.

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?

Despite lacking an output schema, the description provides enough context for correct invocation: prerequisites, parameter semantics, side effects, error condition, and post-condition. The agent knows what triggers a conflict, what happens to credits, and what the tool does not do (apply proposals).

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?

With 0% schema description coverage, the description fully carries parameter meaning. It explains that approvedEstimatedCredits must be the exact pre-approved estimate and that a changed estimate causes a conflict requiring renewed approval. It also defines humanApproved as evidence of human approval, not an agent decision.

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 clearly states the verb and resource: start or retry prompt set analysis after obtaining human approval of the credit estimate. It also distinguishes this from the read-only sibling get_prompt_set_analysis by emphasizing the action of starting/retrying an analysis run.

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?

The description clearly indicates when to use it: before starting or retrying analysis, and it notes that an active run is reused. It does not explicitly name alternatives or when not to use it, but the context is clear and actionable.

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