reject_refinement

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

Goes well beyond the annotations: it explains that destructiveHint means the proposal becomes 'dismissed and terminal, so it cannot be retried' while explicitly scoping what is NOT destroyed ('does not delete or overwrite the underlying memory or page'). It also discloses an environment constraint the annotations cannot express — unavailable over remote HTTP MCP transport, local stdio only.

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 sentences, each carrying distinct load: purpose plus precondition first, then terminal-state consequences and what is untouched, then no-op and transport caveats. No repetition and nothing wasted.

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 single-parameter, non-idempotent-looking mutation with no output schema, the description covers the precondition, the irreversible consequence, the blast radius, and the transport restriction. Nothing an agent needs in order to call it correctly 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 100%, so the schema already documents the single id parameter. The description still adds useful semantics by clarifying the id must reference an item from a listed refinement proposal and that exactly one is operated on, disambiguating it from memory or page ids.

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 with scope: 'Reject one listed refinement proposal by id.' An agent can immediately tell this is the negative counterpart to accepting a refinement. It never names the sibling accept_refinement explicitly, so differentiation is by inference from the verb rather than by direct contrast.

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?

'only after the user gives an unambiguous item-level reject decision' sets a clear, strict precondition for calling, and 'Skip or cancel is a no-op' tells the agent when not to bother. It stops short of naming the alternative tool (accept_refinement) for the opposite decision, so the routing guidance is strong but not fully explicit.

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