record_catch_event

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

Annotations already declare a non-read-only, non-idempotent, destructive write, so the agent knows the safety profile. The description adds only that human_reasoning is 'optional but gold when present' and offers no disclosure of what the destructiveHint implies here, whether records can be amended, or what the call returns. Given it labels itself 'log', a reader might reasonably assume append-only safety, which the destructive annotation undercuts—so the prose undersells the annotation rather than reinforcing it.

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 action and appropriately short, but two of the four sentences are rhetorical framing ('system working, not failure', 'whether catches lead to better decisions') that consume space without helping an agent call the tool correctly.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. But for a tool with a 7-field enum-driven event payload, the description never situates the call in a workflow or clarifies the jargon it depends on, leaving an agent without enough to decide when this event should be recorded.

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?

Top-level schema coverage is reported at 0%, but the single top-level param is a nested object whose properties each carry their own schema descriptions (triggers, actions, assessments). The description's only parameter contribution is the note that human_reasoning is optional and high-value, which is genuinely additive but does not compensate for the coverage gap elsewhere.

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 verb (Log) and a resource (Catch firing), and the enum values in the schema imply a structured event record. However, 'Catch firing' is opaque domain jargon with no gloss, and the description does nothing to distinguish this tool from the many sibling 'record_*' tools (record_handoff, record_gate_skip, record_session_declaration).

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 guidance, no prerequisites, and no named alternatives. The sentences about catches being 'system working, not failure' are motivational framing rather than operational conditions for invoking the tool.

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