Record a task observation

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

Annotations already cover the safety profile (write, non-destructive, idempotent), so the description correctly spends its budget on what annotations cannot express: the record is unvalidated, and consolidation deliberately treats it as weaker evidence requiring more independent sightings before becoming durable memory. That downstream lifecycle behavior is exactly the kind of context an agent needs; only the return/acknowledgement behavior is left unstated.

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?

Two tight sentences with the core capability front-loaded before the comparative note about record_task_lesson. No filler, though the parenthetical and the 'L1' label add mild noise without adding meaning for an outside caller.

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?

The lifecycle framing is good and no output schema exists, so nothing more is owed on returns. However, for a five-parameter, four-required write tool with zero schema descriptions, the definition never explains the required inputs, so an agent can call it but cannot call it confidently.

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 0% across five parameters, so the description must carry the load, and it does not. It hints that a task is involved (task_id) but says nothing about statement, category, the outcome enum, or what idempotency_key means or how it deduplicates, leaving the agent to guess field content and semantics.

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 and resource ('capture an unvalidated observation for a task') and explicitly distinguishes itself from the sibling record_task_lesson by evidence weight. The undefined jargon 'L1' slightly obscures the exact resource being created, but the contrast with the sibling makes selection unambiguous.

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 use condition — 'no validation/artifact needed' — and positions itself against record_task_lesson as the lighter-weight alternative. It does not name exclusions against the other record_* siblings (record_decision, record_rule, record_procedure_outcome), so it stops short of full routing guidance.

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