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

Annotations already set readOnlyHint=false, destructiveHint=false and idempotentHint=false, and the description earns its keep by adding the queue semantics ('lands in the owner's confirm queue', 'nothing changes until they accept') and the auth model (OAuth own-model or scoped contributionToken). It does not mention that duplicate proposals are possible despite idempotentHint=false, which would have been useful.

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?

Three compact sentences, front-loaded with the action before the behavioral and auth details. No filler and nothing repeated from the title or annotations.

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 an output schema present, return values need not be explained, and the description covers the queue lifecycle and both auth paths. The remaining shortfall is the undocumented modelId parameter and the batch constraints, which an agent would have to read from the schema.

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 33%, with items and modelId carrying no schema descriptions, so the description must compensate. It contributes a real constraint on the source field ('provenance pointers only, no free text'), but says nothing about modelId or the item batch limit of 50, leaving the coverage gap only partly closed.

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 and resource ('propose a refinement') and immediately bounds the payload ('provenance pointers only'), so an agent knows exactly what it is submitting. It stops short of naming apply_refinement as the sibling that actually commits the change, leaving that routing implicit.

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 lands in the owner's confirm queue — nothing changes until they accept' tells the agent this is the non-committal path, which implicitly contrasts with the apply tool. But there is no explicit when-to-use statement or named alternative, so the agent must infer that apply_refinement is the follow-up.

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