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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so safety is covered. The description adds real behavioral context beyond them: the run may not be finished yet and results are only returned 'when they're ready', which tells the agent to expect a pending state and poll. It stops short of saying what a not-ready call actually returns.

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?

One sentence, zero waste, with the resource and the payoff front-loaded. Nothing is padded or repeated from the title.

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?

With no output schema, the description carries the burden of explaining return values, and it only says 'get its results' without indicating shape, pending/error states, or whether results persist. For a polling tool this leaves a meaningful gap, though the annotations and 100%-covered schema keep it functional.

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?

Single parameter with 100% schema description coverage, so the schema already explains run_id and ties it to run_my_recipe. The description adds nothing further about format or validity, 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 ('check on') and resource ('recipe or workflow run') plus the outcome ('get its results'). It is distinguishable from run_my_recipe and resume_recipe_run, though it does not explicitly separate itself from the sibling get_job, which likely polls non-recipe jobs.

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?

Usage is only implied: the schema note 'The run id from run_my_recipe' tells an agent to call this after starting a run, and 'when they're ready' hints at polling. There is no explicit when-to-use/when-not, no guidance on polling cadence, and no pointer to resume_recipe_run for stalled runs or get_job for other job types.

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