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

Goes well beyond the annotations: discloses quota metering ('counts against the account's monthly Monte Carlo quota'), refusal semantics for unrecognized node types, seed replay guarantees, the nearest-rank percentile method, and how failedTrials are excluded from statistics. It also explains why the default result is a digest rather than the per-trial array (3.5 MB for a 1000-trial run), which is exactly the kind of non-obvious behavior an agent cannot infer.

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 purpose before diving into result semantics, and every sentence is substantive rather than filler. It is dense and runs long, but the density is earned by otherwise-undocumented behaviors like the digest default and quota cost.

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 correctly carries the full return-value burden, enumerating `seed`, `failedTrials`, `unconvergedTrials`, `summary`, and `nodeStats` in detail. The main gap is that it does not explain how this synchronous, metered run relates to `run_monte_carlo_job`, nor does it mention expected runtime for large trial counts.

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 the schema already carries the per-parameter burden (baseline 3). The description adds real meaning on top: byte-identical replay tied to `seed`, the reason to keep `options.trials` at 50 or fewer with `includeTrials`, and the keyed format of the per-trial `inputs` map.

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?

Strong specific verb+resource: 'Run a multi-trial Monte Carlo tolerance analysis entirely server-side,' with concrete detail on what is randomized and what is reported. However it never distinguishes itself from the sibling `run_monte_carlo_job`, which an agent could easily confuse with this synchronous metered tool.

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 clear when-to-use guidance for `includeTrials: true` ('only when you need the per-trial inputs for sensitivity analysis') and for the default digest path, plus routes quota checks to `get_account_usage`. It states no explicit exclusion against the async sibling `run_monte_carlo_job`, which is the one routing decision an agent most needs.

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