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

Beyond the annotations (destructiveHint=true, idempotentHint=true), the description adds genuinely new behavioral facts: removal can take up to 30 seconds, at least one key must remain on the machine, the operation has no billing impact, and key material is never returned—only fingerprints. These are exactly the operational constraints an agent cannot infer from the annotations or schema.

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 description is dense and front-loaded: purpose first, then per-parameter modes, then constraints and billing. Some sentences are clipped into fragments (e.g., 'Free: it changes no billing.', 'With only instance_id: the keys on it'), which is efficient but slightly awkward to parse; no sentence is outright waste.

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 four-parameter mutation tool with no output schema, the description covers what an agent needs: which modes exist, the rotation pattern, a time expectation, a hard constraint on removing the last key, and the return shape (fingerprints only, never keys). Nothing material is left to inference.

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 75% and each of the three optional parameters is already documented in the schema. The description still adds meaning: it links add_ssh_key_ids to saved keys from list_ssh_keys, clarifies that add_public_keys is 'the .pub file's line', and frames remove_fingerprints in terms of revocation and rotation, which the schema does not explain.

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 opens with a specific compound verb set and resource: 'List, add or take off the SSH keys that can log in to a running machine.' It also names the machine scope (instance_id) and what is returned (fingerprints, comment, key name), so an agent can distinguish this from sibling tools like get_instance or list_ssh_keys without opening the schema.

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?

It maps each parameter mode to an intent: only instance_id to list, add_ssh_key_ids/add_public_keys to grant access, remove_fingerprints to revoke, and it gives the rotation recipe (add new + remove old in one call). It does not name any alternative tool or state when *not* to use this one, so it falls short of full when/when-not coverage.

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