l2kc_submit_job

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

With no annotations, the description carries the full burden and does substantial work: it warns that mock data are test fixtures, states dry_run does not submit, discloses that idempotency_key returns the existing job with deduplicated=true, that a mismatched spec is an invalid-input error, and that an ambiguous submit is not resubmitted. Gaps remain — no mention of auth requirements or what happens to an already-queued job — which keeps this from a 5.

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 fixture caveat is usefully front-loaded, but the body is a stream of telegraphic, backticked fragments with no grouping by concern (provider, memory, idempotency, quota). Every clause is substantive, yet the lack of structure makes it slower to extract the actionable rules than a short ordered list would be.

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 12-parameter mutation tool with no annotations, the description covers scheduling behavior reasonably well, and an output schema exists so return values need not be explained. Still, several parameters and the auth/precondition story are undocumented, and the reference to non-schema fields suggests the description is describing a broader spec than this tool's schema.

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% across 12 parameters, so the description must compensate. It explains provider=auto, high_mem mapping, timeout_seconds' role in CCU budgeting, idempotency_key, account pinning, dry_run and allow_premium, but leaves name, gpu_count, script_path, gpu_type and min_gpu_memory_gb_per_gpu undefined. It also references `mode: real` and `allow_real_jobs`, which do not exist in the schema, adding confusion rather than clarity.

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?

"Submit a script" gives a verb and an object, but the object is under-described — nothing says it submits a GPU/compute job to a scheduler, which the rest of the text only implies. There is a twin sibling, gpu_submit_job, and the description never distinguishes this tool from it, nor from l2kc_recommend_backend even though it mentions dry_run recommends a backend.

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?

Usage conditions are implied through parameter-level rules (premium GPU needs allow_premium, Colab needs timeout_seconds, real jobs need mode: real), but there is no explicit "use this when / use X instead" routing and no exclusions. An agent must infer the workflow from caveats rather than being told where this tool sits relative to list/get/cancel/recommend siblings.

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