ssh_job_output

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

Beyond the readOnlyHint annotation, the description discloses critical behavioral details: the tool is non-consuming (reading again never overlaps or skips a line), merges stdout/stderr, and uses a server-side cursor (the answer names the next offset). This goes beyond the schema and gives the agent confidence that this is a safe, idempotent read-only operation. No contradiction with annotations.

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 sentences, each earning its place. The first gives the core action, the second explains the offset contract, and the third redirects to a sibling for a different concern. No redundancy, perfectly front-loaded.

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 read-only tool with no output schema, the description covers the essential behavior: how to page through output (offset), what data is returned (stdout+stderr), and how to know if more is available (next offset). It could mention error cases like invalid job ID or end-of-output behavior, but the schema and annotations carry a lot of weight. Minor gap keeps it from a 5.

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 100% (all three parameters have descriptions). The description reinforces the meaning of 'offset' by explaining the next-offset pattern, which is helpful. However, it does not clarify the 'profile' parameter beyond the schema's 'Machine name', and the description does not compensate for that ambiguity. Baseline of 3 is appropriate.

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 clearly states the tool 'Returns what a detached job has written so far' with explicit details on stream merging ('stdout and stderr together') and pagination ('from a byte offset you choose'). It differentiates from the sibling ssh_job_status by pointing out that status is not this tool's purpose. The verb 'Returns' is specific and the resource is well-defined.

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 tells the agent when to use this tool (when you need the output of a detached job) and when not to ('For whether the job is still running, ssh_job_status answers in one line'). It also implies usage context by referencing detached jobs from ssh_exec with detach:true in the parameter schema, so the agent knows the prerequisite.

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