Delete sticker

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

Annotations already declare destructiveHint=true, but the description adds crucial context beyond that: the first call changes nothing and returns a preview plus confirm_token, and only the subsequent call with the token deletes. This reveals the non-obvious two-step behavior, which is essential for safe use. It also clarifies that destructive action is gated by the token, fully aligning with annotations.

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?

The description is a single well-structured sentence that leads with the action, then immediately explains the critical confirmation mechanism. No filler or redundant phrases; every word contributes. It is concise yet information-dense.

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 tool with a two-step confirmation pattern, the description covers the essential workflow and return value (preview + token). It does not explain the exact preview format, the dry_run parameter's behavior, or edge cases like invalid tokens, but the core safe-usage context is present. Given the complexity of the confirmation flow, this is quite complete, though not exhaustive.

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 50% (sticker and guild have descriptions; dry_run and confirm_token do not). The description adds meaning to confirm_token by explaining it comes from the first call and is required to complete deletion. However, the dry_run parameter is not explicitly explained; the description implies a dry-run behavior but does not clarify whether dry_run is a flag or if the first call automatically dry-runs. This leaves a significant semantic gap.

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?

The description states a clear verb-resource pair: 'Delete a custom sticker.' It distinguishes this tool from siblings like delete_emoji by specifying 'sticker' and adds the qualifier 'custom,' making the scope precise. The confirmation-flow detail further clarifies the tool's unique purpose compared to a straightforward delete.

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?

The description provides explicit usage guidance by explaining the two-step confirmation process: the first call is a dry-run preview and the second call with a token performs the deletion. It also states 'Safe to call directly,' which sets expectations for first use. However, it does not mention alternatives or when not to use this tool (e.g., for emojis) or prerequisites like required permissions, leaving a minor gap.

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