trust_new_host_key

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

With no annotations, the description carries the full burden and does well: it explains the actual mechanism (the old key is forgotten, the next check accepts whatever key is presented) and flags the security risk and the need for user confirmation. It stops short of stating reversibility, required privileges, or any response behavior.

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?

Three tight sentences: purpose first, then the narrow applicability condition, then the safety caution. No redundancy and nothing that fails to earn its place.

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 one-parameter tool with full schema coverage and no output schema, the description covers purpose, preconditions, and the risk/confirmation requirement. Minor gaps: no statement of what is returned or whether the operation can be undone.

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% and the sole 'host' parameter is documented in-schema with format examples ('192.168.1.10 or host:2222'). The description adds no additional parameter meaning, so the baseline of 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 concrete verb and resource ('Forgets the remembered SSH key') plus the downstream effect ('so the next check trusts the key it presents now'), which resolves the ambiguity in the tool name 'trust_new_host_key'. It does not distinguish itself from siblings, but the sibling list is entirely media/cluster-job tooling, so differentiation is largely moot.

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 scopes use to 'a host the user rebuilt or reinstalled' and adds a when-not signal via the impersonation warning ('an unexpected key change can mean another machine is impersonating it'), plus a required workflow step ('Confirm with the user first'). This is textbook usage guidance for an agent.

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