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

Annotations declare this is a non-read, non-idempotent, non-destructive write; the description adds real value beyond them by disclosing the authorization requirement (OAuth or editToken) and the semantics of the write (appends evidence pointers, nudges confidence, one logged revision). It stops short of describing reversibility or rate/limit behavior, keeping it out of the top band.

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 tight sentences, front-loaded with the core action, followed immediately by the routing rule and auth note. No filler or restatement of the title.

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?

An output schema exists so return values need not be explained, and the description covers auth, effect, and the sibling alternative. What remains thin is the per-item payload semantics (why up to 50 items, how evidence maps to a revision), which the description leaves to 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%, so the schema does not carry the burden alone. The description explains editToken via the auth sentence and implicitly covers 'direction' through 'nudge confidence', but patternId, source, and observedAt semantics come entirely from the schema, and the description adds no syntax or constraints for them.

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 ('Apply a refinement') plus the concrete effect ('one logged revision ... append evidence pointers, nudge confidence'), so the agent knows exactly what happens. The modifier 'directly' distinguishes it from the propose sibling without needing to open either 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?

Explicitly routes the agent: 'Prefer propose_refinement unless the owner asked for direct writes.' Names the alternative and the condition that selects this tool instead, and adds the auth path (OAuth own model or editToken) needed to actually invoke it.

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