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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds real context beyond them: precisely which artifacts are destroyed (file, transcript, other results), that the action is irreversible, and that it overrides the default 24-hour retention window. It stops short of covering auth failure modes or behavior when the job is already gone.

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 short sentences, front-loaded with the action and its scope, then the timing/irreversibility caveat. No filler; every clause carries semantics.

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 two-required-parameter destructive tool with no output schema, the description plus annotations cover what is deleted, that it cannot be undone, and how it differs from automatic expiry. Only edge-case behavior (missing/already-deleted job, permission failures) is unaddressed, which is a minor gap.

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% — job_id's provenance and robot_key's auth role are both documented in the schema itself. The description adds no parameter-level detail, so the baseline 3 applies.

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 gives a specific verb (delete) plus the exact scope of what is removed — the uploaded file, the transcript and all other results — and explicitly contrasts it with the default 24-hour retention. That scope statement cleanly separates it from read-oriented siblings like get_job and list_jobs.

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 states the operative condition clearly: use this to remove results 'right away, instead of 24 hours after the last activity,' which tells the agent when immediate deletion is warranted. It does not name alternatives or state prerequisites (e.g., an in-progress job), so it falls short of a full when/when-not treatment.

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