ssh_forget_host_key

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

No annotations are provided, so the description carries the behavioral burden. It discloses that the operation is a mutation (removing a host-key pin) and adds security-critical context about not retrying silently. It does not detail every side effect, but for this narrow tool the core behavior is clearly communicated.

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 short sentences deliver the action, the condition, and the rationale with no filler. The most important warning is placed immediately after the action, making the structure efficient and easy to parse.

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 two-parameter tool with no output schema, the description covers what it does, when to use it, and why misuse is dangerous. It does not explicitly state the postcondition (e.g., reconnecting to accept the new key), but the essential context for correct invocation is present.

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% and the description does not mention host or port semantics beyond the implicit 'host' in the tool phrase. The parameters are simple and self-explanatory, but the description does not compensate for the missing schema descriptions, so the agent gets minimal additional guidance.

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 verb and object: 'Снять закрепление ключа хоста' (unpin/remove the host key pin). This clearly identifies the operation and distinguishes it from siblings like ssh_forget_server (which forgets a server) and ssh_keys_list (which lists keys).

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 explicitly states the only condition under which the tool should be called: after the user has confirmed the server was recreated. It also gives a negative condition by warning that silently retrying after a key mismatch is exactly what an interceptor wants, guiding the agent not to abuse the tool.

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