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

readOnlyHint=true already declares the non-mutating profile, and the description usefully reinforces it by stating that polling neither starts work nor settles payment. It adds no detail on what job states can be returned, error conditions, or how recovery_capability affects behavior, so it goes only slightly beyond the annotation.

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?

Two short sentences, front-loaded with the purpose and followed by the key polling guarantee. No filler or repetition.

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 should at least sketch what the job state contains and what values it can take, plus what recovery_capability is for. Neither the return shape nor the parameter meaning is covered, leaving a polling tool materially under-described.

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% for both required parameters. The description only restates their names ('with job_id and recovery_capability') without explaining format, origin, or the unusual semantics of recovery_capability, so it fails to compensate for the coverage gap.

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 ('Read a conformance job state'), which is clear on its own. It does not distinguish itself from sibling get_scan_report or list_conformance_checks, so an agent must infer the boundary between reading status and reading a report.

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 phrase 'Polling never starts work or settles payment' implies this tool is the intended polling endpoint and is safe to call repeatedly, which is useful implied guidance. It never explicitly says when to use this versus get_scan_report, nor does it state prerequisites for obtaining a job_id or recovery_capability.

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