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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=false→destructive false), but the description adds substantive behavior the annotations cannot: the app re-derives the headline from the elements, rejects mismatched-attempt/model/dataset verdicts, requires a frozen preregistration for acceptance, and notes that only a protected acceptance verdict moves the job's gate outcome while re-posting is a no-op. This is unusually rich disclosure for a mutation endpoint.

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?

The critical constraint — what the app refuses and what actually moves the gate outcome — is front-loaded before the scope restriction. It is dense and jargon-heavy but every sentence carries a rule; only the parenthetical script path is arguably expendable.

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 non-idempotent-looking write with a nested object payload, no output schema, and full schema coverage, the description supplies the validation semantics, the idempotency/no-op behavior, the outcome effect and the caller scope. Nothing an agent needs to invoke it correctly is missing.

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% across all four parameters, so the schema already documents projectId, jobId, verdict and the superadmin-only customerId. The description adds a note that the verdict must be the record exactly as gate.ts wrote it and is parsed field by field, but no additional per-parameter syntax or format detail. Baseline 3 is 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?

The description states a specific verb and resource — report a verdict written by the frozen gate harness against the job it was measured for — and names the producing artifact (scripts/supplier-risk/gate/gate.ts). An agent can distinguish this write path from the sibling get_gate_result read path without opening either 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?

It gives strong when-not guidance: verdicts bound to another attempt, model or dataset version are refused, an acceptance verdict without a frozen preregistration is refused, and a second acceptance verdict for the job is refused. It also states the caller scope explicitly ('runner — held literally; write, admin and superadmin keys cannot call it'). It never names an alternative sibling for the read case, so it stops short of the 5-level explicit routing.

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