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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds valuable context: existing servers are unaffected, the key can simply be added again, and authentication is required. It also discloses the two-phase nature and the need for user confirmation, which annotations cannot convey. No contradiction with annotations; the destructive label applies to the eventual confirmed action.

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 information-dense sentences covering purpose, side effects, reversibility, authentication, return value, and next step. The leading 'deleteSshKey:' echoes the tool name but is immediately followed by substance. Every sentence earns its place, though the description is slightly long for such a focused tool.

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?

Despite having no output schema, the description explicitly names the returned actionId and the required follow-up action, so the agent knows exactly what to do next. It also covers safety-relevant effects and reversibility. For a staged destructive operation, nothing essential is missing.

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 input schema covers both parameters at 100%, including that keyId is an integer from listMySshKeys and how sessionKey should be handled. The description adds no extra parameter-level detail, so baseline 3 is appropriate since the schema does the heavy lifting.

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 operation: staging removal of an SSH key from the account. It distinguishes itself from addSshKey (opposite action) and executeConfirmedAction (follow-up action). The word 'Stage' makes clear this is not immediate deletion.

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?

Describes the intended workflow explicitly: returns an actionId, present the summary to the user, then call executeConfirmedAction with the actionId if approved. This gives clear guidance on when this tool is used versus its confirmation sibling. It doesn't enumerate all alternatives, but the workflow framing is sufficiently directive.

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