gate_verdict

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

With no annotations, the description carries the full burden and does well: it discloses that the server applies thresholds/markers in code, that ratings are logged, that ratings gate only relevance, and that inflation corrupts the loop. It omits what the successful return value looks like beyond the 🟡/0 failure marker.

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?

A single dense paragraph that front-loads the phase, mode, and action before the constraints. Little waste, though the fail-closed clause repeats the fail-closed concept already implied by the threshold/validation statements.

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 nested-object, no-output-schema, no-annotation tool, it covers the essential contract: inputs, validation, server-side decisioning, logging, and failure behavior. Only the shape of a successful verdict is left unspecified.

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%, but the description compensates: it defines the ratings payload shape {id: 0-3}, the per-candidate requirement, and the origin of the nonce. advisor_dir is explained in the schema itself (must match the nonce's advisor).

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?

The description names a specific action (phase-2 judging of 'cite', host mode) and a specific resource (relevance ratings submitted via a judgment_request nonce). It clearly positions itself as the second phase of the cite workflow, though it does not name an alternative sibling to route away from.

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?

It states the trigger condition (you hold a nonce from judgment_request), the required coverage (ratings for EVERY candidate), and the failure condition (bad/expired/reused nonce or missing ratings → fail-closed). It does not explicitly name alternative tools, but the sequencing guidance is clear.

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