firefighter_submit

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

Annotations declare destructiveHint=true and openWorldHint=true, and the description adds meaningful context beyond them: the command runs as the user, outside any agent sandbox, with the user's network and files, plus an explicit caution to only submit what you'd run in your own shell. It also discloses the return shape ('one line: job id, start estimate, cost, do: (next step)'), so the agent knows what comes back and what to do next.

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?

Four short sentences, front-loaded with the core purpose and threshold, then sequencing, then the safety-critical caveat last. No filler, and each sentence carries distinct 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?

For an 11-parameter destructive job-submission tool with no output schema, the description covers purpose, when to submit, sequencing, execution environment, and the shape of the response. It leaves unstated what happens on failure or how to poll progress outside of firefighter_wait, but the essentials for calling it safely are present.

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%, so every parameter including cost modifiers (spot, urgent, minutes lease) is already documented in the schema. The description adds no parameter-level meaning beyond that; its remaining content concerns execution environment and return value, not argument semantics.

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 states a specific verb and resource ('Queue heavy work') and scopes it precisely with the inclusion threshold ('GPU, or CPU over ~1 min') and the shared-machine context. It is clearly distinguishable from siblings by naming firefighter_wait as the immediate follow-up.

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 gives a concrete use condition (heavy work: GPU, or CPU over ~1 min) and an explicit next step ('Then call firefighter_wait'), which routes the agent correctly after submission. It stops short of stating when not to use it (e.g. short CPU work, or when firefighter_plan/status is the better starting point), so it is not fully explicit about alternatives.

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