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

With no annotations, the description carries the burden well: it discloses the resulting state (proposed, not accepted), the auth requirement with the three accepted header forms, and the validation rule that proposed_by must be a roster agent. It omits idempotency/duplicate handling and rate limits, but the safety-relevant behavior is covered.

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?

Four short sentences, front-loaded with purpose and state, then requirements, then the routing exclusion. No restated title or filler.

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?

An output schema exists, so return values need not be explained. Auth, the proposed/applied state, the roster constraint, and the accept path are all present; only the semantics of title/body/department content are unaddressed.

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% across 4 parameters, so the description must compensate. It only adds meaning for one parameter (proposed_by must be a roster agent); title, body, and department are left to inference from their names, which is acceptable but not compensating for the coverage gap.

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?

Specific verb + resource ('File an org lesson into SharedBrain') plus the resulting state ('stored as proposed'). It explicitly contrasts itself with the sibling accept_lesson, so an agent can tell the two apart without opening a 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?

Clear when-to-use framing and an explicit when-not plus alternative: 'Promoting it to accepted is accept_lesson. This tool does not accept it.' It does not distinguish itself from the other submit_* siblings (submit_finding, submit_daily_note, submit_spaces_intel), which is the only gap.

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