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

With no annotations, the description carries the burden. It discloses the async nature (returns scan id, requires polling) and the page limit, but omits potential side effects, authentication needs, or rate limits. The behavioral disclosure is adequate but not exhaustive.

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 front-loaded sentences: first gives the core action, second provides technical details (page limits, mode, polling). No unnecessary words; every sentence earns its place.

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?

The description covers the main flow (submit, get scan id, poll for report), but lacks error handling, timeouts, or mention of the scan id format. Siblings are referenced properly (poll get_report/get_report_markdown). For a 3-param tool with no output schema, it is mostly complete.

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?

Despite 100% schema coverage, the description adds meaningful context: explains max_pages defaults and max, clarifies mode='instant' as a single-page quick check, and notes that max_pages is ignored for instant mode. This goes beyond the schema's dry parameter descriptions.

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 it submits a URL for an SEO audit, specifies crawling behavior and result retrieval via polling, and distinguishes from siblings like get_report and get_report_markdown by establishing this as the initiation step.

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 implies this is the tool to start a scan, but does not explicitly state when to use it vs siblings (e.g., diff_scan or get_report). No when-not-to-use guidance is provided, though the polling mention hints at the asynchronous workflow.

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