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

With readOnlyHint=false already signaling a write, the description adds behavioral context by explaining this writes to the swarm's memory-of-itself and enforces a validity rule: the named fact rows must exist or the input is just an opinion. It does not cover error behavior or auth, but the annotations plus this context are sufficient.

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 three sentences, front-loads the action and object, and uses each sentence for either the core operation or a meaningful constraint. The 'opinion' sentence is slightly rhetorical but it effectively communicates the validation requirement without being padded.

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-parameter write tool with fully described schema fields and annotations, the description covers purpose, provenance constraints, and the multi-fact scope. It does not describe the return value, but this is a minor gap given the strong schema coverage and the explicit conceptual framing.

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 100%, so the schema already documents type, content, confidence, and derived_from. The description reinforces that derived_from must name existing fact ids and that content should be checkable, but it adds no parameter-level detail beyond the schema.

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 opens with a specific verb ('Record') and names the object types (pattern, anomaly, insight, warning), plus the required provenance (fact ids it was derived from). It also differentiates this tool from single-fact writes by stating 'This layer is for observations that span more than one fact, which is exactly what no single fact can say.'

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 a clear usage condition: use this layer when an observation spans multiple facts, and it states that all derived_from fact ids must exist. It does not explicitly name an alternative like write_fact for single-fact records, but the contrast with 'no single fact can say' strongly implies the boundary.

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