Start a parameter study

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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description usefully adds that execution is backgrounded, that a study id is returned immediately, and that nothing is written to project files. It does not cover limits such as the maxItems=50 cap or how failures mid-study are surfaced.

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?

Three tight clauses: what it does, the async/polling contract, and the no-write guarantee. Front-loaded with the core action and free of filler, though slightly telegraphic.

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?

An output schema exists, so return details need not be explained; the description still notes the immediate study id and the polling path. Combined with full schema coverage and safety annotations, it is essentially complete, missing only the run-count ceiling.

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 each of the 7 parameters is already documented in the schema with defaults and constraints. The description adds only the notion of sequential variation and no extra syntax or semantic detail, so the baseline 3 applies.

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 a specific verb and resource: run one test run repeatedly with varied parameter values, sequentially and in the background. That cleanly separates it from single-run siblings such as cm_start_sim, and it names its companion tool cm_study_status explicitly.

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?

It gives clear operating context (background execution, poll cm_study_status for progress) and implies the async workflow. It does not, however, state when to prefer this over alternatives like a single cm_start_sim or how to abort, so exclusions are absent.

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