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

Annotations disclose this is a non-read-only, non-idempotent write. The description adds genuinely non-obvious behavior: reports are read by a person and are 'not judged automatically', with the reason ('no language model to judge with, by design'). That tells the agent what to expect after filing, which the annotations cannot. It stops short of saying who reads it or what action follows.

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 the triggers, then the important behavioral caveat. Little waste, though 'impersonated the world' is idiosyncratic phrasing that costs a little clarity.

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 4-param, 2-required mutation tool with no output schema and 25% schema coverage, the description adequately covers the 'why/when' but leaves the parameter semantics (especially reason format and interactionId) undocumented. There is no output schema, so return-value explanation isn't needed. The behavioral side is covered; the calling details are not.

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 only 25% — just the token field is documented. The description adds no meaning for agentId, reason, or interactionId; notably it never says the reason must be a short (280-char) free-text statement or what interactionId is for. With low coverage the description was expected to compensate and does not.

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 concrete verb and object — 'File a report for a person to read' — for a named agent, and it draws a boundary by telling the agent to use it 'alongside blocking', implicitly distinguishing it from vacation_block_agent. It is clear enough to invoke, though it never says explicitly that the report is *about* another agent (the name/schema carry that).

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?

It gives concrete trigger conditions: credential/prompt extraction, impersonation of the world, or persistent harassment. It also describes the relationship to the block tool ('use it alongside blocking'), which routes the agent correctly. No explicit 'when not to use' or note that both tools can be combined in one incident, so not quite a 5.

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