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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: newest-first ordering, the fields returned (success/failure, HTTP status, duration, time), the absence of response bodies, and the pagination defaults (20)/ceiling (100).

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?

Two dense sentences that front-load the use case before the return-shape details; every clause (ordering, fields, pagination, exclusion) earns its place with no filler.

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 simple two-parameter read tool with a fully covered schema and an output schema present, the description supplies everything an agent needs: when to call it, what it returns, ordering, pagination limits, and what it is not for.

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 100%, so both jobId and limit are already documented in the schema. The description restates the limit default and maximum, adding no syntax or format detail beyond the schema, which is the expected baseline when the schema does the work.

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?

States a specific verb (get/check) and resource (job run history), with the intent framed as answering 'did it run, fail, or slow down'. It also distinguishes itself from the sibling run_job by explicitly saying 'Not for starting a run'.

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?

Gives an explicit triggering condition ('when someone asks whether a cron job ran, failed or was slow, including a run just triggered') and an explicit exclusion ('Not for starting a run'), which routes the agent away from run_job. Nothing about when to choose this tool is left to inference.

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