Verify citations

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

Annotations cover the safety profile (readOnly, idempotent, closed-world), and the description adds substantial behavior beyond that: what is verified against (working tree or a git ref), the return shape (a 0.0-1.0 grounding score), and the failure categories produced (drifted, hallucinated, invalid). Since there is no output schema, disclosing the score and flags here is genuinely necessary and valuable.

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 tight sentences: verification scope first, return values second, usage cue last. Every sentence carries distinct information and nothing is repeated.

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 and only a small optional-parameter surface, the description supplies exactly what an agent needs: what gets verified, what the result means, and when to reach for it. Nothing material is missing for correct invocation.

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 description coverage is 100%, so `ref`, `repo`, `findings` and `findings_path` are already documented, and the description largely restates them (git ref, findings document). The one added nuance is that findings may come from another model's output, which the schema does not say. Baseline 3 is appropriate when the schema carries the parameter burden.

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 (verify that each cited span/snippet/symbol in a findings document exists in the repo) and enumerates the exact citation kinds checked. This is clearly distinguishable from omniseek_scan (produces findings) and omniseek_render_dossier (renders them) without opening any schema.

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?

"Use it on findings you or another model wrote" gives clear context for invocation, and the schema's reference to findings "as returned by omniseek_scan" chains it into the workflow. It stops short of naming an alternative or stating when not to use it (e.g. verifying against uncommitted work vs a ref), so it is not a full 5.

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