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

Goes well beyond annotations by disclosing irreversibility, exactly what stops (API requests, OAuth-created webhooks) versus what keeps running (queued posts, cloud patrol settings, API-key webhooks), that pending confirmations are cancelled, the post-state 401 key_disabled, and the important side effect that a consent-page connection is shared across all sessions of a platform like claude.ai. This is exactly the context annotations cannot carry.

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 critical fact — permanent, irreversible self-disable — is front-loaded, and every clause carries distinct operational information. It is a dense paragraph with nested parentheticals that could be split for readability, but little is genuinely redundant.

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 no output schema, the description steps in to describe the return value (the list of cancelled confirmation requests) and the post-call behavior (401 key_disabled). Combined with the destructive-annotation coverage, an agent has everything needed to call and explain this safely.

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 tool takes no parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly makes no attempt to invent parameter meaning.

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 ('Permanently disables') and a precisely scoped resource ('the key or connection making this call'), and immediately clarifies it acts only on the calling credential rather than any arbitrary key. There is no sibling that overlaps this self-revocation semantics, so the agent can distinguish it cleanly.

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 final sentence gives explicit triggering conditions: leaked credential or the user asking to stop this connection permanently. It does not name an alternative tool (none exists among siblings), so the guidance is clear but stops short of when-not-to-use framing.

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