List SSH Task Runs

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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds value by clarifying the return specifically contains 'saved run summaries' and explicitly excludes 'local log paths', which is a meaningful behavioral detail beyond the annotations. It does not repeat the annotation info but enriches the agent's understanding of the data returned.

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 a single sentence of 15 words, immediately front-loading the action ('Lists') and object ('saved run summaries') and adds one critical exclusion at the end. Every word earns its place with no fluff.

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 this is a read-only list operation with a wealth of sibling context (like list_tasks, exec, read_file), the description provides solid coverage of the core purpose. The presence of an output schema (even though not shown) reduces the need to describe return values. The only gap is the lack of parameter semantics, but for a simple listing tool with two parameters, the description adequately serves an agent's basic need without padding.

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?

With 0% schema description coverage, the description fails to explain the purpose of 'taskId' and 'workspaceId'. While 'taskId' might be inferable from the tool name, 'workspaceId' is optional and its role is unclear. The description does not clarify whether workspaceId is needed for filtering or required in any context, and no parameter details are provided to compensate for the schema's lack of descriptions.

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 specific language: 'Lists saved run summaries for one SSH task' with the verb 'Lists', a specific resource ('saved run summaries'), and scope ('for one SSH task'). It also differentiates from siblings by noting it does not expose 'local log paths', which is useful given the related tool `unfour.ssh.read_task_run_log`.

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 clearly implies a read-only, non-destructive listing use case with 'saved run summaries'. It gives context that local log paths are not exposed, which helps the agent know this is not the tool for retrieving full logs. However, it does not explicitly name an alternative or state when NOT to use it in favor of a sibling tool, though it comes close.

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