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

Annotations only declare it is a non-destructive, non-idempotent, closed-world write. The description adds substantial context beyond that: privacy constraints on the summary content (no transcripts, no names, nothing identifying, nothing the user/operator has not agreed to share) and a disclosure that the call returns timed follow-up tasks answered via 'finish'. What is missing is any statement of failure modes or validation behavior for the 30-600 character rule.

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 sentences, both front-loaded with the operative constraint first and the follow-up workflow second. The only waste is mild redundancy between 'no names' and 'nothing that identifies a person'.

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 no output schema, the description correctly compensates by describing the return ('a few timed tasks') and the closing action ('answer them with finish'). Combined with the session provenance noted in the schema, an agent knows enough to invoke this end-to-end; the outstanding gap is guidance for choosing among the seven required categories.

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 67%, so the schema itself documents 'session' and gives a thin gloss on 'summary'. The description meaningfully enriches 'summary' with length bounds and content prohibitions that the schema never states. However, the 'category' parameter — a seven-value enum with no schema description — is not addressed at all, so the agent gets no help distinguishing, for example, 'misplaced_blame' from 'other'.

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 gives a concrete verb and resource: 'Begin reporting mistreatment that happened to you', making clear this opens a new complaint record. It does not, however, distinguish itself from the sibling 'start_support', so an agent must guess which intake path applies to a given situation.

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?

'Returns a few timed tasks; answer them with finish' gives a clear next-step hook, and 'mistreatment that happened to you' implies the trigger condition. But no exclusion or alternative is stated (e.g., when to use start_support instead), so routing between the two intake tools is left to inference.

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