Clear SSH Task Runs

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

The annotations already disclose destructiveHint=true and readOnlyHint=false. The description adds the important detail that both data records and local log files are removed, and that a guarded confirmation policy is mandatory. This goes beyond the raw annotations without contradicting them.

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?

Two concise, front-loaded sentences with no superfluous text. The first sentence establishes the core action and scope, the second sentence gives a critical policy caveat.

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?

Given the destructive nature and five parameters, the description covers the basic scope and safety requirement but omits the relationship between taskId and workspaceId and the precise confirmation flow. The output schema is provided, so return values are not needed in the description, but enough ambiguity remains to warrant a middling score.

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 compensate, but it provides only high-level hints about the parameters ('one task or the workspace' and 'content-bound confirmation'). The meaning of five parameters, including the duplicate confirmationText/confirmation_text fields and how to satisfy the guard, are left unresolved.

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 uses a specific verb, 'Deletes', names the destroyed resources ('SSH task run records and local log files'), and defines scope ('for one task or the workspace'). It clearly distinguishes this tool from siblings like cancel_task_run or delete_task, which affect different resources.

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?

The description conveys when to use the tool: when permanently removing saved run history and logs for a task or workspace. The 'Guarded policy requires confirment' clause provides a usage constraint, but it does not explicitly name alternatives or state when not to use it.

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