palinode_correction_dismiss

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

Goes well beyond the annotations: it clarifies that no memory is written, that the queue row is marked dismissed and kept, and that the reason is mandatory and stored. This reconciles with destructiveHint=false and readOnlyHint=false by explaining exactly what state changes and what is preserved.

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 tight sentences, front-loaded with the action, then the state effect, then the rationale for the required parameter. No filler; each sentence carries distinct information.

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 only two fully documented parameters, annotations covering the safety profile, and no output schema, the description supplies everything needed: what it does, what it writes, what it preserves, and why the reason is required.

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 baseline is 3, but the description adds real meaning: it stresses the reason is required and explains why (a dismissal without one is indistinguishable from an unlooked-at candidate), reinforcing that the reason is the durable record.

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+resource: recording that a correction candidate was reviewed and declined. It clearly distinguishes itself from siblings like palinode_correction_apply or palinode_correction_undo by naming the exact action and target (the candidate's queue row).

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?

Explains the context in which it is used (after a candidate is reviewed and declined) and gives the consequence (prevents a later transcript scan from re-proposing the same span). It does not explicitly name the sibling alternatives such as apply/undo, but the usage situation is clear.

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