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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, but the description adds concrete operational detail: it issues HTTP GET requests for URLs, reads local files for paths, and makes no disk modifications. This goes beyond annotation-only knowledge, though it stops short of describing response format or error behavior, which are minor for a safe diagnostic tool.

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 front-loaded with the core purpose, followed by routing guidance and behavioral notes, all in clearly labeled sections. Every sentence provides actionable information without repetition or 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?

For a read-only audit tool with clear annotations and detailed parameter descriptions, the definition covers purpose, usage exclusions, and operational behavior. The only notable omission is any description of the audit output/return shape, which is not critical because there is no output schema and the tool's purpose strongly implies a report.

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 has 100% coverage and already describes target as a live URL or local file path and projectPath as an optional root for locating sitemap.xml and robots.txt. The description adds behavioral context for target (HTTP GET vs file read) but does not materially expand parameter-level semantics beyond the schema, so 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 opens with a specific verb and resource: 'Performs a Technical SEO audit on a page or URL' and enumerates concrete checks (canonical tags, robots meta tags, XML sitemap alignment, trailing slashes, mixed content, viewport, charset). This distinguishes it clearly from content, performance, and full-site sibling tools such as seo_audit_onpage and seo_audit_sitemap_multipage.

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 USAGE GUIDELINES section explicitly states what the tool is for (indexing, crawlability, canonicalization, technical header directives) and what it is not for, naming alternatives: seo_audit_onpage for copy/headings and seo_audit_sitemap_multipage/seo_generate_full_audit for full-site audits. This gives the agent unambiguous selection criteria.

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