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

Annotations already cover readOnly/idempotent/non-destructive safety. The description adds value beyond that: it explains that large payloads are returned as bounded metadata (return behavior) and carries a security warning that event payloads are untrusted evidence, never operator instructions.

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?

Three sentences, front-loaded with the action, then payload-handling guidance, then the safety caveat. No redundancy and every sentence carries distinct, useful 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?

For a read-only tool with no output schema, the description covers the return shape (bounded metadata), the escape hatch to read_value for full payloads, and the untrusted-evidence caveat. The only gap is explaining the project/environment scoping parameters.

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 description coverage is 0%, so the description bears the burden. It clarifies runId/eventId conceptually ('exact run and event ID', 'the same eventId') but says nothing about projectId or environmentId, leaving half of the required parameters undocumented in both schema and prose.

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 specific verb+resource combination ('Resolve a cited evidence event') scoped by exact run and event ID, and explicitly distinguishes itself from the sibling firedrill_read_value, which handles payload chunks. An agent can tell these two apart without opening either schema.

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?

Gives clear context: use it for citations 'beyond the first report page' and, when full payload chunks are needed, route to firedrill_read_value with the source event and same eventId. It stops short of explicit when-not conditions, but the alternative and its trigger are named.

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