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

With no annotations, the description carries the full load: it makes clear this is a write ('record') and discloses the downstream effect on aggregates and the false-reject sample, which is useful. It omits whether a verdict can be reviewed multiple times, whether the verdict must already exist, and what happens on failure or duplicate submission.

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?

One sentence, front-loaded with the core action and scope, then the parameter details and downstream effect. No filler or restatement of the tool name.

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 4-required-parameter mutation tool with no annotations and no output schema, the description covers purpose, enum values, and downstream impact. Remaining gaps (duplicate reviews per verdict, referential requirements on verdict_id, units/format) are modest.

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 0%, so the description must compensate, and it largely does: it supplies the allowed values for queue (verdict_first|fifo) and human_decision (land|reject) that are absent from the schema, and clarifies reviewer_minutes as time spent. verdict_id is only implied ('for a verdict'), leaving one parameter undocumented.

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) and resource (an actual human review measurement for a verdict), plus names the data captured. It is distinguishable from siblings like verdict_submit or governor_record, though it never explicitly contrasts itself with them.

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?

The emphasis on 'ACTUAL' hints that this is for real measurements rather than simulated/estimated ones, and it names the downstream consumers (reviewer-time aggregates, false-reject sample), which implies why to call it. However, there is no explicit when-not guidance or named alternative among the siblings.

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