submit_run

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

With no annotations provided, the description carries the full burden. It discloses async behavior and prerequisites (NONMEM installation) but omits critical behavioral details like file system side effects, error handling if the executable is missing, queue behavior, or whether operations are idempotent.

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 with zero waste. Front-loaded with the core action ('Submit'), followed by return value and prerequisites. Every clause earns its place.

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?

Given the lack of output schema and annotations, the description adequately covers the return value (job ID) but omits details about output artifacts, error formats, or lifecycle management that would help an agent handle the async operation robustly.

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?

The input schema has 100% description coverage, documenting all four parameters (ctl_path, work_dir, nmfe_path, run_name) including defaults. The description adds no additional parameter semantics beyond the schema, meeting the baseline expectation for high-coverage schemas.

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 clearly states the tool submits a NONMEM run with specific async behavior. It distinguishes itself from sibling status-checking tools by mentioning it returns a job ID for polling. However, it doesn't explicitly differentiate from similar execution tools like 'execute_psn_bootstrap' or 'execute_psn_vpc'.

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?

The description implies a polling workflow by stating it returns a 'job ID for polling,' suggesting the use of 'check_run_status'. It also notes the NONMEM installation prerequisite. However, it lacks explicit guidance on when to use this versus PSN-based execution siblings or cancellation policies.

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