run_sweep

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), it discloses genuinely useful behavior: clones are created, jobs start in the background, they execute serially one after another, and the maximum is 8 values. It does not explain the preview vs final `mode` behavior or whether clones persist, which is relevant for a mutating tool that creates cases.

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?

Dense and front-loaded: the core semantics come first, followed by the convergence variant and then the polling/comparison follow-up. The inline examples earn their space by making `path` and `values` concrete; nothing is obviously redundant.

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 6-parameter mutating tool with no output schema, the description covers the workflow and the most complex parameter well, but leaves `mode` (preview vs final), `language`, and the exact return shape unexplained. An agent knows how to sequence the call but not the full contract.

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 0%, so the description must carry parameter meaning, and it does explain `path` (with several concrete example paths), `values`, and the `study` enum. However, `case_id`, `mode`, and `language` receive no explanation at all, leaving half the parameters undocumented across both schema and description.

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 names a specific operation (parameter study / sweep) and resource (one clone of the case per value of `path`), and distinguishes it from a single run by stating that each value spawns a separate background job. An agent can immediately tell this apart from `run_simulation` or `clone_case`.

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 a concrete workflow: run the sweep, poll each job_id with job_status, then compare_runs on the case_ids. It also explains the study="convergence" variant. It does not say when to prefer this over repeated run_simulation calls or what to do at the 8-value ceiling, so it stops short of full when/when-not guidance.

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