query_agent_run_telemetry

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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description reinforces this with 'Read-only'. It adds behavioral details beyond annotations: pagination defaults (page 1, limit 25), the return structure (data, total, page, limit, pages), and that it searches across all organization runs. This is comprehensive for a read-only search 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?

The description is a single, information-dense sentence with no fluff. It front-loads the main action, includes pagination defaults, filter categories, an alternative-tool pointer, read-only note, and return structure—all in under 50 words. Every clause earns its place.

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?

With 9 optional filters and no output schema, the description covers return fields and pagination, and provides filter grouping. It does not explicitly state that filters can be combined (which is implied) or mention the max limit of 200 (already in schema). Overall, it gives sufficient information for an agent to call the tool correctly, though it could be slightly more explicit about filter combination.

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 coverage is 100%, so each parameter is already documented. The description adds semantic grouping: 'run_id, telemetry_kind, or module_name to pinpoint' vs 'status, request_hash, policy_snapshot_id, or schema_snapshot_id for lineage audits'. This helps the agent understand intent and choose filters appropriately, going beyond individual descriptions.

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 states a specific action (search telemetry batches), a clear resource (runtime telemetry across all agent runs), and explicitly differentiates from the sibling get_agent_run_telemetry by noting when to use each. This is unambiguous and distinguishes the tool from other query tools.

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?

Explicitly names the alternative tool (get_agent_run_telemetry) and the condition for using it (when run_id is known). It also groups filters into 'pinpoint' vs 'lineage audits', giving context on typical use cases. No exclusions or conditions are left to inference.

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