pbs_job_run

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

With no annotations, the description carries full responsibility. It clearly labels the tool as a mutation, details the return schema quirk (null vs UPID), explains risk per job_type (e.g., prune deletes snapshots), and mentions config requirement (PROXIMO_PBS_*). This is thorough, though it could add more about error states or idempotency.

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 description is dense and contains a lot of information, but it lacks structure. It mixes purpose, schema quirk, risk, and config in a single paragraph. Starting with 'MUTATION:' is good, but the text could be more organized (e.g., separate behavior, return type, risk). Some redundancy with schema.

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 tool's complexity (mutation, multiple job types, return quirks, config dependencies), the description covers essential aspects: purpose, dry-run gate, risk per type, config requirement, and return behavior. An output schema exists, so return values are defined there. Missing: typical use cases, error handling, or impact on job scheduling. Still, it's fairly complete.

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 coverage is 100%, so the baseline is 3. The description adds marginal value beyond the schema: it repeats the confirm gate and job_type values, and adds a config note. It does not clarify job_id further. The SCHEMA QUIRK note is about return values, not parameters.

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 triggers a PBS scheduled job immediately, differentiating it from job management tools (create, delete, update). It specifies the job_type options (sync, verify, prune) and notes it's a mutation, but could more explicitly contrast with siblings like pbs_prune or pbs_verify_start.

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 explains the dry-run vs execution gate (confirm=True), which is helpful. However, it does not provide guidance on when to use this tool versus alternatives like pbs_prune or pbs_verify_start for on-demand runs. No prerequisites or exclusions are mentioned.

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