Dismiss posts

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

Annotations already declare destructiveHint=true, but the description adds real value beyond them: exactly which states are affected vs. spared, and that write scope is required. It doesn't cover reversibility or rate/confirmation behavior, but with annotations carrying the destructive profile this is solid extra context.

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?

Four short, front-loaded sentences. The eligible-state scope comes first, followed by the exclusion, the reason guidance, and the auth requirement. No sentence is padding.

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 destructive mutation with an output schema, the description covers scope, exclusion, auth, and optional-parameter intent, so an agent can call it correctly. Return values are handled by the output schema, leaving little 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 description coverage is 100%, so both parameters are already documented. The note 'Pass the user's reason when they gave one' reinforces the optionality of reason but adds little syntax or meaning beyond the schema's own 'if they said' description. Baseline 3 is appropriate.

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 (cancel/dismiss) and resource (posts) and enumerates the eligible states (proposed, scheduled, failed, handed-off). It implicitly differentiates from posts_publish by stating 'Nothing already publishing or published is touched,' but never names a sibling tool to route the agent between them.

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?

Provides clear context for when the tool applies (cancel posts in the four pre-publish states) and an exclusion ('nothing already publishing or published'). It stops short of naming alternatives like posts_publish or posts_approve or stating any explicit when-not-to-use beyond the state filter.

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