Record a task lesson

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

Annotations already establish this is a non-destructive, idempotent write, so the safety profile is covered. The description does hint at a tiered evidence model (L1 auto-captured vs L3 requiring human approval), which is real context beyond the annotations, but it never explains what those tiers mean or what the idempotency_key and validation_id do.

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 short clause with no filler and the core action front-loaded. It is appropriately sized in form, though that brevity stems partly from saying almost nothing.

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 7-required-parameter evidence-recording tool with no output schema and only minimal annotations, the description is far too thin. It omits parameter meanings, the L1/L3 taxonomy, idempotency semantics, and any notion of what constitutes a valid lesson or how the referenced artifacts/validation are resolved.

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?

All 7 parameters are required with 0% schema description coverage, and the description supplies no meaning for any of them — not task_id, category, statement, artifact_ids, validation_id, source_refs, or idempotency_key. With zero structured coverage, the description was the only place to compensate and it does nothing.

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 verb 'capture' plus 'task-owned reported evidence' gestures at a write action, but the object is opaque: 'L1' and 'L3' are undefined jargon, and nothing distinguishes this from siblings like record_task_observation or record_procedure_outcome. An agent cannot tell what a 'task lesson' actually is.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as an alternative despite several closely related record_* tools. The clause about L3 needing human approval implies a workflow boundary but never states the condition for choosing this tool.

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