Stop Meta pushing events for a Page

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

With annotations marking destructiveHint and idempotentHint, the description enriches this by detailing the exact scope ('removes the WHOLE subscription'), the side-effect-free nature ('Nothing published or posted is affected'), and the critical verification behavior ('THE ANSWER IS THE READ-BACK...'). It also notes the credit cost ('0 credits'), providing full transparency of what the tool actually does and how to interpret results.

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?

Every sentence adds value: the core action, the all-or-nothing caveat, the safety note, the verification method, and the credit cost. Information is front-loaded with the primary purpose, and nothing is redundant. The length is justified given the subtlety of the operation.

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?

The description is complete for a destructive operation with a single optional parameter. It explains the behavior, the verification step, the side effects, and the cost. It doesn't include a return format, but that's not expected given no output schema, and the read-back description hints at the response. Combined with annotations, an agent has everything needed to call and interpret this tool correctly.

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?

The schema covers the only parameter (pageId) with a clear description ('Facebook Page id — omit when only one Page is connected'). The tool description doesn't add further parameter semantics beyond restating the context. With 100% schema coverage, a baseline of 3 is appropriate, as the description doesn't reduce ambiguity but also doesn't need to.

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 exactly what the tool does: 'Remove this app’s webhook subscription from a Page, so Meta stops pushing its events.' It uses a specific verb ('Remove') and resource ('webhook subscription from a Page'), and explicitly contrasts with sibling tools like subscribe_meta_webhooks by noting the full-subscription removal. This clearly distinguishes it from related tools.

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 practical guidance: it explains the all-or-nothing nature (Meta’s DELETE takes no field list) and tells the user to call subscribe_meta_webhooks if they want to keep some fields. It also clarifies the effect ('Nothing published or posted is affected; only the notifications stop') and the verification method via read-back. However, it doesn't explicitly mention when to use meta_webhook_status or other alternatives, leaving some room.

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