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

The annotations only say readOnly=false and destructive=false; the description adds the substantive behavior — the call stores a staged proposal, nothing is transmitted, and the person must confirm out-of-band at welance.com/directory, with a review link returned. It omits any warning that repeated calls are not idempotent (idempotentHint=false) and would create additional draft proposals.

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?

"nothing is sent," "Stores a proposal only," and "Nothing happens until the person confirms it" all restate the same non-transmission guarantee across three sentences. The opening is a noun fragment rather than a front-loaded verb, though the description is still short enough to scan.

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 four required parameters and no output schema, the description covers the key unknowns: the approval model, the external confirmation step, and the fact that the result carries a review link. Missing only failure conditions (invalid briefId, team not owned) and the non-idempotency caveat.

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 50%: text and summary are documented in-schema, while briefId and teamKey are not. The description compensates by qualifying teamKey as "one of the person's teams" and briefId as "an open brief," which tells the agent the ownership and state constraints the bare integer/string schema 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 the resource precisely — an anonymous pitch draft for a team (teamKey) on an open brief (briefId) — and makes the draft-vs-send distinction explicit with "nothing is sent. Stores a proposal only." It never names the sibling propose_pitch_send, so the differentiation is inferable rather than declared.

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 useful preconditions (a team the person belongs to, an open brief) and describes the confirmation flow on welance.com/directory. However, it never tells the agent when to choose this over propose_pitch_send or propose_brief_draft, leaving the alternative selection to inference.

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