Record a bounded candidate-workbench event

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

The description adds context not captured by the annotations: it records structured diagnostics, is App-only, and accepts only a fixed enum rather than free-form text. However, it does not disclose side effects, persistence behavior, or what happens if required identifiers are invalid, which matters for a non-read-only 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?

Two short sentences and a clear title, with no filler or duplicated schema details. The description front-loads the most important constraints: internal-only and fixed-enum diagnostics.

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 tool has seven parameters, sparse annotations, and no output schema, yet the description only explains the event constraint. It omits context for required IDs, metric fields, side effects, and intended invocation scenarios, making it incomplete for an agent selecting and invoking the tool correctly.

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?

With 0% schema description coverage and seven parameters, the description must compensate, but it only mentions the event enum and the absence of arbitrary log text. Required parameters such as resultSetId and candidateId are left completely unexplained, and optional metrics like durationMs and payloadBytes receive no semantic guidance.

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 title and description clearly identify a recording operation: 'Record a bounded candidate-workbench event' and 'structured diagnostics.' The added restriction to a 'fixed event enum and no arbitrary log text' distinguishes it from generic logging or free-form reporting. It is somewhat domain-specific, but the purpose is comprehensible.

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 description notes 'Internal App-only,' implying it should be used by the internal application rather than end users or external callers. It also implies a diagnostic/telemetry context, but it does not explicitly say when to use this tool versus any alternative or mention exclusions beyond 'no arbitrary log text.'

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