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

Goes well beyond the annotations by disclosing the validation refusals (mismatched attempt/model/dataset version, acceptance without preregistration, duplicate acceptance verdict), that only a protected acceptance verdict moves the gate outcome, and that re-posting is a no-op. This substantively enriches the idempotent/non-destructive hints.

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-loads the core action and then layers conditions and scope. Dense and jargon-heavy, but each sentence earns its place and the SCOPE constraint is clearly delineated at the end.

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 mutation tool with no output schema, it covers behavior, validation refusals, auth scope, and idempotency well. Only minor gaps remain, such as the response format of a successful recording beyond the no-op case.

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 100%, so the baseline is 3, but the description adds real meaning: the verdict is parsed field by field exactly as gate.ts wrote it and the headline is re-derived from its elements, and jobId is the job the verdict was measured for. This clarifies the nested verdict object beyond the schema's terse note.

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 (record/report) and resource (a gate verdict from the frozen gate harness) tied to a measured job. It even names the exact producer (scripts/supplier-risk/gate/gate.ts), letting an agent distinguish it from get_gate_result without opening a 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?

Provides explicit call conditions: it is for the training runner's key and write/admin/superadmin keys cannot call it, plus the prerequisite that the verdict must come from the frozen harness and that acceptance requires a frozen preregistration. No alternative tool is named, but the context is clear and actionable.

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