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

Annotations establish the safety profile (mutation, idempotent, destructive), and the description adds real context beyond them: the Enterprise governance feature prerequisite, the DRAFT state the proposal opens in, and the terminal state change ('idea flips to PROMOTED and links to what it became'). It doesn't explain error/failure behavior or what happens to linked artifacts, but the added side-effect and prerequisite detail is substantial.

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?

Front-loaded with the one-line purpose, then two parallel sentences for the two lanes, closing with a decision heuristic. No filler and every clause carries operational meaning.

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 mutation with no output schema, the description covers purpose, lane selection, prerequisites, and resulting state. It leaves minor gaps (permissions beyond the Enterprise gate, behavior on failure), but nothing essential to invoking it correctly is missing.

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 50%, but the description compensates well: it explains the 'target' enum semantics (two lanes) and the conditional 'projectId' requirement ('when the idea is still General'). 'assigneeId' is only documented in the schema and 'ideaId' is not elaborated, but the added meaning for the two most consequential params is significant.

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 ('promote') and resource ('an idea') plus the two concrete outcomes (task or DRAFT proposal). It is immediately distinguishable from siblings like create_task, create_proposal, and update_idea because it transforms an existing idea rather than creating a fresh entity.

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 clearly frames when each lane applies ('task' for small/clear/do-it-now, 'proposal' for material investment) and even advises 'most ideas are tasks.' It stops short of naming alternative tools (e.g. create_task directly or update_idea) or stating when not to use this tool at all, so it is strong context without explicit exclusions.

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