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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely useful non-schema behavior: the verdict taxonomy, the fact that it returns a deciding quote, the 6-citation cap, and the exact cost model ($0.005 + $0.006/citation, $0.041 per x402 call). Remaining gaps are minor (fetch failures, timeouts, paywall handling).

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 the core action and its four verdicts, then cost. One dense sentence plus a pricing sentence, with no filler. The pricing detail is somewhat dense but earns its place because cost is not available in any structured field.

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?

With no output schema, the description must convey return shape, and it does: per-citation verdict plus deciding quote. Cost, cap, and read-only nature are all covered. The main omission is the unresolved url/claim vs citations invocation model for a 3-param, 0-required tool.

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 coverage is only 33% (only 'citations' is documented), so the description has to compensate. It partly does: it explains that claim and url form a cited pair and that 'citations' is JSON [{claim,url}] capped at 6. It never clarifies the ambiguity of three parameters with zero required — whether url+claim are a single-pair alternative to the batch 'citations' array, or must accompany it.

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 and resource — reads a cited source and judges whether it supports a claim — and enumerates the exact output verdicts (supported, partial, not supported, contradicted) plus the deciding quote. That is far more specific than the sibling 'cite' or 'links_check', and an agent can tell instantly what this returns.

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 task context is implied ('for each claim and the URL cited for it'), so an agent can infer this is for post-hoc citation verification, but the description never states when to prefer this over the sibling 'cite' or 'links_check', nor any preconditions (e.g. source must be publicly fetchable). Usage is inferable, not directed.

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