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

Annotations already cover the safety profile (readOnly, non-destructive, open-world), and the description adds meaningful context beyond them: provenance caveats (bounded crawl sample), validation performed at run time (source ownership, version, expiry, membership), and sampling limitations. This is useful behavioral disclosure an agent needs to interpret results cautiously.

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?

Four tightly packed sentences with the core purpose front-loaded and caveats following. Little waste, though 'typed source evidence and missing-field diagnostics' borders on opaque filler rather than earning 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?

For a tool with no output schema, zero parameter documentation, and four undocumented inputs, the description leaves critical calling details blank. It explains data provenance well but never tells the agent what the parameters mean or what fields come back, so an agent cannot reliably invoke it correctly.

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% across all four parameters, so the schema provides no semantic help, and the description never mentions task_id, pageUrl, limit, or keywordLength. The phrase 'bounded crawl sample' faintly implies a sampling limit, but nothing documents what each parameter controls.

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 states the resource (page keyword density) and its scope (bounded crawl sample), but there is no clear verb and no explanation of what the metrics actually contain. 'Returns typed source evidence and missing-field diagnostics' is jargon that doesn't clarify the tool's output for an agent comparing it to the many sibling SEO keyword tools.

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?

There is no explicit when-to-use guidance and no named alternative among the numerous sibling SEO/keyword tools. The only routing hint is a negative scope statement ('does not describe every page'), which tells the agent what data it won't get rather than when to select this tool over others.

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