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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), but the description adds substantial behavioral context: deterministic rule-based scoring with no LLM, same input yields same score, naturalness is returned but excluded from the total, and no guarantee of actual AI citation.

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?

Front-loaded with purpose and return shape, then caveats and the alternative. Dense but every sentence carries information; the criteria enumeration and elaborated GEO definition are slightly verbose but relevant to interpreting the score.

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?

Even though an output schema exists, the description explains what the score means, how it is computed, its limitations, and the fallback path. Nothing an agent needs to select and invoke this tool correctly is missing.

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?

Only one parameter at 100% schema coverage, so the schema already documents the URL and its constraints. The description adds no format or syntax detail beyond confirming it fetches a public page, so the baseline of 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?

Opens with a specific verb+resource ('Fetch a public web page and compute its GEO score') and immediately defines the score semantics. It distinguishes itself from the sibling by naming score_text as the fallback for login/JS-only pages.

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 states the condition under which to use the alternative ('Pages behind a login or rendered only by JavaScript may not be fetchable: use score_text with the page text instead'). Also clarifies cost/auth/storage expectations (free, no API key, nothing stored).

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