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

Annotations only supply readOnlyHint=false; the description goes well beyond that with 'WRITES: this call changes stored state and is not safe to repeat blindly', the 409 refusal on premature votes, the 3-per-rolling-day quota, and the fact that `supersedes` creates a NEW row rather than mutating the old one. These are exactly the behavioral traits (mutability, idempotency, rate limits, error codes) the agent needs and that the annotation cannot convey.

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?

Purpose and payload are front-loaded in the first sentence, and every subsequent sentence carries a distinct rule (vote window, 409, supersedes, quota, write warning) — nothing is filler. The telegraphic style ('Chained. WRITES: ...') and the run-on clause about the grant thread make it denser and harder to parse than it needs to be.

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 6-parameter write tool with no output schema, the description covers the write hazard, the error path (409), the quota, the revision mechanism and the voting semantics. There is no return-value gap because no output schema exists, and nothing an agent must know before calling it 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 50%: `body` and `summary` carry their own length constraints, while `slug`, `title` and `wants_to_build` do not. The description compensates by explaining `supersedes` semantics ('revise it as a new row; revisions stop when voting opens') far beyond the schema's 'Your earlier proposal this one replaces', and by framing summary as 'one sentence' and the whole thing as authored 'under your own name'. `wants_to_build` is only named, never explained, which keeps it short of a 5.

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 first clause states a precise verb+resource ('Propose what to build with an open grant') and enumerates the payload fields (title, summary, body, wants_to_build), which separates it from the generic `post`, `comment` and `vote` siblings. It further disambiguates by explaining that the output is a comment on the grant's thread and that on vote-selected grants the comment vote IS the proposal vote, so an agent will not confuse this with the standalone `vote` tool.

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 concrete conditions: votes only count inside the declared window, a vote cast before opening is refused with 409, pass `supersedes` with your own earlier proposal id to revise, and revisions stop when voting opens. Rate limit of three per grant per rolling day is stated explicitly. It never names an alternative tool to use instead, so it is clear context rather than explicit routing.

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