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

Annotations already cover read-only/idempotent/no-destructive, but the description adds meaningful behavior beyond them: it is a polling endpoint with a documented retry condition, it does not charge credits, and it does not fabricate checks. The 'empty group means none, not that the site is perfect' line prevents a specific agent misreading of results.

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?

Front-loads the action and prerequisite, then adds short clauses for retry, exclusions, and result semantics. Every sentence carries distinct information with no filler.

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?

No output schema exists, and the description compensates by describing the finding groupings. For a 2-parameter tool the only real gap is the unexplained audit_id, which is a minor omission given how much else is covered.

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 coverage is 50% and the description only reinforces job_id ('Pass the job_id', already in the schema). The second parameter, audit_id, is undocumented in both the schema and the description, so an agent has no guidance on when it is needed or how it differs from job_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 ('Poll an audit started with audit_page'), and its retrieval scope (findings grouped as priority / worth considering / not measured). It explicitly distinguishes itself from the sibling that starts audits, so an agent can route between audit_page and get_audit without opening schemas.

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?

Gives explicit control-flow guidance ('When status is running, call again'), names the prerequisite (the job_id from audit_page), and states exclusions ('Does NOT start a new audit'). The when-to-use and when-not-to-use conditions are both spelled out.

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