check_job

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

No annotations are provided, so the description carries full responsibility. It discloses that the tool queries current state, returns an exact set of possible states including NOT FOUND and UNKNOWN, and explains the 'last' resolution. It does not describe side effects (likely none), permissions, nor what happens on errors (e.g., if connection fails). But for a read-only status check, the state list and resolution semantics add transparency beyond the schema. It doesn't mention whether it disconnects or changes connection, but the sibling 'reconnect' and 'status' tools suggest connection state is separate.

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 compact and efficient: a one-line purpose, a helpfully formatted state list, and a terse but sufficient parameter explanation. It front-loads the core purpose and immediately gives the actionable info (states and the 'last' special value). No wasted words; every sentence 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 one parameter, no annotations, a simple output schema (not shown but likely a state string or enum), and low schema coverage, the description provides enough for an agent to call correctly: it defines the parameter format, explains special 'last', and enumerates possible return values. However, it doesn't specify the output schema format (e.g., whether it returns a string or object) nor error handling for missing job id. But with only one param and the tool's simplicity, the gap is minor, so 4 is justified.

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 0%, and the schema only says 'job_id' is a string with no description. The description's argument section adds meaning: 'job_id: JES job id (e.g., JOB01234)', and clarifies the special literal 'last'. This adds meaning beyond the schema's bare property name. However, it doesn't specify format constraints beyond example, nor does it clarify if whitespace matters. Still, for a single param with clear naming, the description adequately compensates for low schema coverage.

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 it returns the current JES state of a job, with a specific resource (job) and an enumeration of possible states. It distinguishes from siblings like list_my_jobs (which lists jobs) because it checks one job's status, not a list. However, it doesn't explicitly differentiate from potential job-status tools, but among the siblings, none check single job status except fetch_sysout, which is for output.

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 usage: call when you need to know the state of a specific job, using its JES id. It defines special value 'last' for the most-recently-submitted job, which is helpful. However, it doesn't explicitly say when NOT to use it vs. alternatives like fetch_sysout (for output) or list_my_jobs (for finding IDs). The guidance is adequate but not explicit about alternatives.

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