submit

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write/safety profile is covered. The description usefully adds the base64-then-sbatch pipeline, which is real behavioral context beyond the annotations, but it omits auth/permission needs and whether the job persists after submission.

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?

A single front-loaded sentence with the verb first, mechanism second, and return value last. No filler or redundancy.

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?

The presence of an output schema means return-value detail (job_id) is already partly covered, and annotations handle the safety profile. However, the 'connection' parameter is unexplained and there is no usage routing, so the definition is adequate but leaves gaps for a write 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 description coverage is 0%, so the description must carry the parameter burden. It clarifies that 'script' is script text that gets base64-encoded on upload, but says nothing about the 'connection' parameter's format or expected value, leaving one of two required params undocumented.

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 and resource (submit a Slurm batch job) and adds mechanism detail (script uploaded as base64, then sbatch) plus the return value (job_id). It is clearly distinguishable from read-only siblings like jobs/status/log, though it does not explicitly contrast itself with exec or alloc.

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?

No guidance on when to use this over exec (interactive run) or alloc (resource allocation) is provided. The description only says what it does, leaving the agent to infer the selection condition from the tool name.

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