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

Annotations only declare readOnly=false, destructive=false, idempotent=false, openWorld=true. The description adds context the annotations cannot: an immutable job record is created per call (explaining the non-readOnly hint), the tool never spends, it may fetch only the single caller-provided URL, and unreachable sources yield a structured source_unavailable error instead of a verdict.

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-loads the verb and resource, then layers side effect, cost, and error behavior; every sentence carries information. It is slightly dense — four stacked clauses plus an example — but nothing is padded.

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 (so return values need not be described), it still names the verdict and source fields, and it covers the mutation side effect, the zero-cost guarantee, the URL-fetch scope, and the error path. An agent has everything needed to call it correctly and interpret the result.

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 exists and schema description coverage is 100%, so the schema already documents length bounds and the 'no Google scraping' constraint. The description restates the same input modes ('pasted SERP or AI-answer text, or one caller-provided public URL') without adding new syntax or format guidance, so the 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?

States a specific verb (verify) and resource (pasted SERP/AI-answer text or one caller-provided public URL) and names the outcome (confirm/contradict/missing verdict with cited sources). It implicitly but clearly distinguishes itself from the paid-evidence siblings by contrasting with 'before quoting or paying for evidence' and 'never spends'.

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 when to use it: 'when an agent needs a confirm, contradict, or missing verdict with cited sources before quoting or paying for evidence,' and adds a concrete example (checking a token launch date claim). It does not name the sibling tools (e.g., aftersearch_quote) as alternatives, so the routing is implied by cost rather than stated.

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