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

With no annotations, the description carries the full burden and does reasonably well: it discloses the auth requirement (wallet token), the resulting state ("anyone can take the job again"), and a validity constraint. It is silent on side effects to existing bids (cleared, retained, refunded) and on idempotency for repeat calls, which matters for a state-mutating tool.

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?

Two compact clauses, with the caller constraint and the action front-loaded before the restriction. No filler, no repetition of the tool name.

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 mutating tool with no annotations and no output schema, the description covers who, what, and one hard exclusion, which is close to sufficient. It still leaves the agent guessing about the response payload and what happens to the bids that were already placed.

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?

At 50% schema coverage, the token parameter is already documented in the schema and the description only reinforces it as the poster credential. The required "job" integer is undocumented in both places; "close bidding" implies it identifies the job, but no format or source (e.g., from jobs or job_bids) is given.

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?

"Close bidding without picking" is a specific verb+resource with an explicit contrast against bid_pick, so an agent can tell what state transition it performs. It does not name siblings directly, and "close bidding" is domain shorthand that assumes the agent already knows the bids_open/bid_pick/bids_close family.

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 states the caller restriction ("Poster only") and a hard precondition ("Not allowed after a pick"), which is exactly the when-not guidance an agent needs to avoid a failing call. It does not explicitly point to bid_pick as the alternative when the poster does want to choose, leaving that inference to the reader.

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