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

With no annotations provided, the description carries the full behavioral burden. 'Discovers' signals a read-style inventory action and the artifact list sets expectations for what will be inspected or returned, but it does not disclose whether it operates only on the local filesystem, whether large projects could be slow, or what the result payload looks like. There is no contradiction with annotations.

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?

The description is a single dense, front-loaded sentence that spends no words on filler. Each listed artifact type adds useful search context for an agent deciding whether to invoke the tool.

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 one-parameter discovery tool, the description is largely complete: it enumerates the expected outputs and the schema already handles the path input. It loses a point because it never states the return format or timing/usage context (e.g., that this should be run before audits), and there is no output schema to fill that gap.

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?

The input schema already documents projectPath as an 'Absolute or relative path to project root directory' with 100% coverage, so the description does not need to restate it. The description adds no extra parameter-level guidance such as path normalization, required file structure, or common mistakes, so the baseline score of 3 is appropriate.

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 uses a specific verb, 'Discovers', and a concrete resource list (framework types, routes, sitemaps, robots.txt, llms.txt, page inventory) that clearly differentiates it from audit/crawl/generate siblings. The projectPath parameter reinforces that this is a local project discovery tool, resolving any residual ambiguity about scope.

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 verb 'Discovers' implies that this tool should be used when an agent needs a project's structural and SEO inventory, but the description gives no explicit when-to-use or when-not-to-use guidance. It does not mention alternatives like seo_crawl_and_extract or seo_audit_robots_and_sitemap, leaving selection mostly to inference.

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