runtime_telemetry_report

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

Annotations already provide readOnlyHint and idempotentHint, so the description adds value by detailing behavioral aspects: the tool returns aggregate counts and a bounded event list, is filterable by multiple criteria, and never writes. This complements the annotations effectively without contradiction.

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?

The description is two sentences: the first summarizes functionality and parameters, the second provides use cases and safety. It is front-loaded with the primary purpose, every sentence has value, and there is no redundancy or fluff.

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?

Given the tool has 8 parameters, an output schema, and is a reporting tool, the description covers purpose, filterable parameters, aggregation output, use cases, and safety. It does not need to detail output fields since the schema exists. The description is complete for an agent to understand the tool's value and invocation context.

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, the description must compensate. It lists filterable parameters (decisionKind, family, requestId, since, until) but omits projectId, projectRef, and limit, though 'bounded list' hints at limit. It explains aggregation dimensions (decisionKind, family, grade), which adds meaning. Overall, partial coverage but not exhaustive.

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 for read-only inspection of mako_usefulness_events, returning aggregate counts and a bounded list of recent events. It specifies the resource and exact operations, and the verb 'inspect' aligns with the read-only nature. Though it does not explicitly compare to siblings, the specific resource name distinguishes it effectively.

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 explicitly states two use cases: verifying usefulness capture and triaging grade emissions. It also notes 'Never writes to the event table,' which is a safety guideline. However, it does not mention when to avoid this tool or provide comparisons to sibling report tools, which would improve guidance.

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