record_verification_feedback

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

With no annotations, the description carries the full burden and does so well: it states it does NOT change the stored ai_completion_score, does not re-run any model, costs nothing (no Anthropic call, only an audit-log row), and is idempotent-safe. This is exactly the behavioral context an agent needs before calling a mutation-adjacent tool.

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-loaded with the core action and its not-a-correction caveat, then the prerequisite, then the no-cost assurance. Dense with em-dashes but every clause earns its place; only slight compression loss in readability.

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?

No output schema and no annotations, yet the description fully covers purpose, prerequisite, mutation scope, cost, and safety. An agent has everything needed to call this correctly on the first attempt.

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 agreed, notes, task_id, and actual_score are already documented in the schema. The description adds context (task_id refers to the task whose most recent verification is being judged) but no syntax or constraint beyond the schema. 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?

States a specific verb (record) and resource (verification feedback) and immediately disambiguates intent: 'calibration data, not a correction.' It distinguishes itself from the sibling verify_task by explaining it attaches to an ai_generations row rather than producing a verdict.

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?

Gives a clear prerequisite — verify_task must have run at least once first — and notes it is safe to call as often as useful. It does not name a competing sibling to route away from, but the context of use is unambiguous.

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