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

Annotations only say readOnly=false, idempotent=true, destructive=false; the description goes well beyond them by disclosing the supersede rule ('a newer one supersedes the older'), the non-destructive guarantee that vendor source rows are never overwritten, how reads are affected by default, and the exact failure behavior (returns a sentence telling the user to accept on the dataset page). That is precisely the context annotations cannot carry.

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 action and consequence, and almost every sentence carries real information. Minor deductions: the overlay paragraph is lengthy for a tool whose job is just to accept, and there is a formatting defect ('accept.Works on your connector tables') that hurts scannability.

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 no output schema, the description still covers the mutation's effect, its reversibility/supersede semantics, the auth requirement, the degraded-path return value, and which datasets it applies to. An agent has everything needed to decide whether to call it and what to tell the user if it fails.

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 100% and both parameters are already documented in the schema, including that ids come from propose_* answers or list_proposals. The description reinforces the 'by id, in bulk' framing but adds no format, limits, or batch-size detail beyond the schema. Baseline 3 is right when the schema does the heavy lifting.

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?

Opens with a specific verb+resource+scope: 'Accept open proposals by id, in bulk.' The verb alone separates it from list_proposals and reject_proposals, and the follow-on sentence explains what an accepted entry actually is (the thing overlay="with_overlay" reads), so an agent knows the effect without opening the 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?

Gives an explicit precondition ('Only call it when the user said which proposals to accept') plus the auth gate (owner's API key marked trusted) and the fallback path (owner accepts on the dataset page under Proposed changes) when that gate fails. It also names the upstream tools that produce the ids, so the agent knows where to get them.

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