job_output

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

Annotations already declare destructiveHint=true and openWorldHint=true; the description corroborates this by explaining exactly what is destroyed (a finished job, after its last output chunk) and adds non-obvious traits the annotations cannot convey, e.g. IDs surviving MCP restarts and duplicate-free pagination.

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, no filler, and the primary purpose is front-loaded ahead of pagination and cleanup details. Every clause carries distinct operational information.

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?

With no output schema, the description should say more about the returned status/output shape, and it omits auth or target-selection prerequisites for a destructive, open-world tool. It covers the main quirks (ID persistence, dedup pagination, cleanup) but is not fully complete for a 5-parameter mutation-capable tool.

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 coverage is only 20%, so the description carries real weight. It explains cleanup and offset/pagination semantics, but it refers to 'next_offset' while the actual schema parameter is 'offset', a naming mismatch, and leaves job_id, limit and the required target unexplained (target's meaning comes from the schema, not the description).

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?

States a specific verb+resource: reading remote background job status and output. It is clearly distinguishable from job_kill (which terminates) and from local read/bash siblings. It stops short of explicitly naming those siblings, so a 4 rather than a 5.

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?

Gives concrete operating guidance: reuse next_offset to paginate without duplicates, and cleanup:true deletes a finished job after the last chunk. It implies when to use cleanup and how to resume, but never states when not to use this tool or what alternative exists for running/completed jobs.

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