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

Annotations already cover readOnly=false, openWorld=true, non-idempotent, non-destructive, but the description adds information annotations cannot express: the ~$0.075 cost, the asynchronous multi-minute latency, the requirement to poll for results, and the workspace-prerequisite failure mode. These are exactly the behavioral traits an agent needs before committing to the call.

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 sentences, front-loaded with purpose and cost, followed by the follow-up/failure routing. Every clause earns its place 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?

Cost, latency, polling, and the error-recovery path are all covered, and an output schema exists so return values need not be explained. The only minor gap is scope detail on what the audit covers beyond the supplied siteId, which the schema partially handles.

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?

There is a single required parameter with 100% schema description coverage ('Site id from list_sites'), so the schema already carries the semantics. The description adds nothing about the parameter, which is the expected baseline when schema coverage is complete.

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 ('Starts a new crawl and audit of a site') and implicitly distinguishes itself from get_site_audit, which it identifies as the polling companion rather than the initiator. An agent can tell exactly what this does without opening the schema.

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?

Explicitly tells the agent what to do after invocation (poll get_site_audit), what to do on failure (call get_setup_status if the workspace is not set up), and names related tools. This is genuine routing guidance covering both the success and error paths, not just an implied context.

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