cortex_job_runs

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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds value by stating raw prompt/model artifacts are NOT included and that it returns {runs: CortexJobRun[]}, which helps set expectations about output. However, it does not disclose any rate limits, pagination, or sort order, and the annotations already cover the safety profile.

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 three sentences, each adding relevant details: the resource and scope, the read-only and exclusion note, and the return shape. It is efficiently written without fluff, though the third sentence about return shape could be considered slightly redundant given no output schema exists, but it is useful.

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 is a read-only list with one parameter and no output schema, the description covers the key aspects: what it returns, what is excluded, and its read-only nature. There is no mention of pagination or ordering, but for a simple audit-trail list tool, this is adequate. The description is complete enough for an agent to call it correctly.

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% (job_id is fully described with format and example). The description does not add parameter-specific meaning beyond the schema, but it clarifies that the tool returns runs for that job, which is already implied by the schema. With full schema coverage, a baseline of 3 is appropriate.

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 states it lists attempt history (audit-trail runs) for a Cortex job, one row per execution attempt with status, model, metrics, timings, and errors. It clearly identifies the resource (Cortex job) and the action (list runs), but does not explicitly distinguish from sibling tools like cortex_get_job or cortex_list_jobs, relying on the term 'attempt history' to imply differentiation.

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 when to use it: to see attempt history for a specific job, and states what is not included (raw prompt/model artifacts). It does not explicitly state when NOT to use it or mention alternatives like cortex_get_job (which might return overall job status). The context of audit-trail runs is clear but exclusions are not.

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