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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), but the description adds genuinely new behavioral context: the entirely heuristic, no-LLM execution model and the shape of what comes back (0-100 score, grade, signal breakdown, ranked fixes). It still does not state latency or rate limits.

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?

Three compact sentences, no filler, with the core purpose front-loaded and the heuristic/return details following. Every clause conveys distinct information.

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 single-parameter, fully documented tool with an output schema, the description supplies the method and return shape needed to call it correctly; return-value detail is not required since an output schema exists. The only real gap is sibling routing, which is a usage concern rather than missing operational context.

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 with 100% schema description coverage, so the schema already carries the semantics (absolute http(s) URL). The description adds no constraint or format detail beyond that, making the baseline 3 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?

States a specific verb (score) and resource (citation likelihood for a URL) and enumerates the public signals inspected, so the agent knows exactly what capability this is. It does not, however, distinguish itself from close siblings like citations_check or citations_evidence, so the boundary must be inferred.

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?

No explicit when-to-use or when-not-to-use guidance, and the many citations_* siblings are never referenced. Usage is only implied by the phrase 'No LLM fired - all heuristic', which suggests a fast, cheap predictive pre-check rather than a full audit.

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