runtime_telemetry_report

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description reinforces these by stating 'Read-only inspection' and 'Never writes to the event table,' and adds behavioral details like returning aggregate counts and a bounded list. No contradictions with annotations.

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 clear, well-structured sentences, front-loaded with the core action and outputs. No extraneous information.

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 description covers purpose, usage, and key filters. It does not detail the output schema (but that is provided separately) or mention pagination. For a report tool with 8 optional parameters and an output schema, it is adequately complete.

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 schema description coverage at 0%, the description must compensate. It mentions four filterable parameters (decisionKind, family, requestId, ISO time window) but omits limit, since, until, projectId, and projectRef. This provides partial but incomplete enrichment over the schema.

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 description clearly states the tool is a read-only inspection over mako_usefulness_events, returning aggregate counts and a bounded list of recent events, with specific filter parameters. It uses specific verbs and resources, distinguishing it from sibling tools like agent_feedback_report, though not explicitly contrasting.

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 provides explicit use cases: 'verify usefulness capture is flowing' and 'triage why a decision site emitted the grade it did,' plus a clear 'Never writes to the event table' disclaimer. However, it does not mention when not to use the tool or name alternative tools.

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