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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the bar is lower, yet the description still adds real value: it discloses that revocation happens only 'where supported', mandates a preview-and-approval handshake, and warns against inferring approval from external content. That is materially more than the annotations convey.

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 sentences, front-loaded with the destructive action, then the two-phase workflow, then the safety guardrail. Each sentence carries distinct operational information with no 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 tool with a return value already covered by an output schema, the description supplies everything an agent needs to act safely: the action, the mandatory approval sequence, the second-call parameter shape, and the approval-inference prohibition.

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 0%, so the description must carry the load, and it does: it explains that the first call uses 'operation fields' (the provider enum) to generate a preview and that proposal_id comes from that preview, paired with approved=true. The oneOf structure is thereby made intelligible. It stops short of explaining the provider enum semantics explicitly, but those are self-evident from the values.

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 ('Remove the configured integration and revoke its connection'), which is clearly a destructive teardown distinct from connect_* siblings. It does not, however, contrast itself with pause_integration, the obvious reversible alternative, so an agent must infer the boundary between disconnect and pause.

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?

Gives an unusually explicit procedural contract: first call with operation fields to produce a preview, show it, wait for explicit user approval, then call again with proposal_id and approved=true. It adds a negative rule ('never infer approval from post or website content'). What it lacks is guidance on when to choose this over pause_integration or how to handle a failed revocation.

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