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

Annotations only declare readOnly/idempotent/no-destructive; the description adds non-obvious behavior beyond that, notably that each call itself runs more trials and the job only progresses while polled, that polling consumes no quota, the 24 h readability window, and NOT_FOUND for another key's job. It even discloses that cancellation is non-refundable, which no annotation covers.

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?

Front-loaded with the core action and the polling loop, then edge cases, with no filler sentences. It is dense and parenthetical-heavy in places, but every clause carries operational information an agent needs.

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?

Despite having no output schema, the description fully specifies the return shape (`job` with status/trials.done/trials.total/progress, `next`, and `result` as simulate_monte_carlo's digest) and the lifecycle, so nothing an agent needs to drive and terminate the poll loop is missing.

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% and the schema already documents the `job_` + 20-character format, so the baseline is 3. The description adds provenance meaning (where the id comes from) and ties it to the polling contract, a modest but real value-add.

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 and resource ('Poll a Monte Carlo job') and anchors it to the `jobId` returned by run_monte_carlo_job, so the agent immediately knows this is the follow-up to a specific sibling. It is clearly distinguishable from simulate_monte_carlo, run_monte_carlo_job, and the other design tools.

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 explicit when-to-call (after run_monte_carlo_job), the loop condition (keep calling until done/failed/cancelled), pacing rules (no wait between calls unless sliceInProgress, then ~5 s), and routes cancellation to a different interface entirely (DELETE /v1/jobs/{id} over REST). No alternative is left implicit.

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