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

Annotations already declare a safe read (readOnlyHint, idempotentHint, non-destructive), and the description adds real value on top: the exact status vocabulary, the polling contract, what it does NOT return (pages or individual issues), and cost ('FREE'). The 'no complete status' note prevents a genuine failure mode.

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-loaded with the purpose and return shape, then constraints, then follow-ups; no filler sentences. The inline field list is dense but earns its place by defining the response contract in the absence of an output schema.

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, but the description compensates by enumerating every returned field, defining the status values, and pointing to the downstream read tools. Nothing an agent needs to poll or hand off correctly is missing.

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 100%, so auditId and projectId are already fully documented in the schema, including the auditId/jobId equivalence and where projectId comes from. The description adds only the implicit lineage to start_site_audit, so the baseline 3 applies.

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 names the exact resource (progress/status of a site audit) and ties it to the sibling that creates it (start_site_audit), then enumerates the returned fields. An agent can immediately distinguish it from get_audit_comparison, get_audit_core_web_vitals, etc.

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?

It gives explicit polling instructions ('poll until it is completed or failed'), an explicit anti-pattern warning ('there is no complete status'), and routes the agent onward to the five reporting siblings once the audit completes. When-to-use and what-to-do-next are both stated.

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