Read SSH File

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable behavioral context beyond these: 'output is capped and line-redacted by the SSH engine' and 'Sensitive paths may still be blocked by connection or OS permissions.' This gives the agent crucial expectations about limits and failure modes.

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 three sentences, front-loaded with the primary action, and every sentence adds distinct value (use cases, environment allowance, output/security behavior). No wasted words or repetition of schema/annotation fields.

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 7 parameters and 0% schema description coverage, the description could have been more thorough about parameter semantics. However, the existence of an output schema covers return value details, and the description explains output caps, redaction, and permission issues. It is reasonably complete for a read-only tool, but not fully exhaustive.

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. It hints at parameter roles via 'bounded remote file slice or tail' (limit/offset/tailLines) and 'through SSH' (connectionId), but it does not explain timeoutMs, workspaceId, or provide per-parameter detail. The compensation is partial, warranting a mid-range score.

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 'Reads a bounded remote file slice or tail through SSH' and explicitly mentions use cases ('logs and config inspection'). It distinguishes itself from siblings like write_file, exec, and read_task_run_log by specifying the bounded file read behavior.

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?

Provides clear context: 'Useful for logs and config inspection' and notes that 'Dev/test/prod allow ordinary reads.' However, it does not explicitly mention when not to use it or compare to similar tools like read_task_run_log, so it lacks full exclusion guidance.

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