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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds substantial context on top: dependent product data goes with it, retention guards still apply, host action confirmation is required, the token is explicitly not consent, and there is no undelete or provider-side erasure. The 'token is not consent' and 'no undelete' points are exactly the behavioral disclosures an agent needs before an irreversible call.

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 irreversible action and its scope are front-loaded, and each subsequent sentence carries a distinct operational fact (prerequisite, exclusion, confirmation, recovery). The telegraphic style — dropped articles, 'Actual host action confirmation is required' — costs some readability but no sentence is filler.

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, non-idempotent mutation with an output schema, the description covers prerequisites, irreversibility, confirmation semantics, and post-failure recovery. The one gap is that 'eligible' channels are never defined and the description never says what dependent product data is at risk, leaving the agent unable to predict the blast radius.

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 all three parameters are already documented, including the expected_impact token source and the stale-snapshot failure mode. The description restates the token requirement without adding syntax, format, or failure detail beyond what the schema provides, so baseline 3 applies.

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 and resource ('Permanently removes ... channel and dependent product data') and scopes the blast radius to dependent product data. It also distinguishes itself from Gmail disconnection, which shares the 'disconnect' space. Slightly undermined by the vague qualifier 'exact eligible channel' — eligibility criteria are never defined.

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?

Explicitly establishes the prerequisite chain (lifecycle authority plus a current token from channel_removal_impact) and names the condition that routes the agent elsewhere: Gmail channels are rejected in favor of their disconnection lifecycle. It also covers the recovery path via channel_removal_status after a lost response, so the agent knows what to do before and after the call.

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