study

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

With no annotations, the description carries the full burden and does disclose key behavior: it writes three named artifacts under mirofish_runs/<name>/, details the contents of study_summary.json, reuses finished cells on rerun, and executes as a background job. It omits cost/runtime expectations and how to retrieve results once the job completes.

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?

Content is front-loaded and nearly every clause adds information, but it is delivered as one dense run-on with an inline schema sketch, making it hard to scan. Some structuring (separate sentences for what it does, the spec shape, and what it writes) would cost nothing.

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?

Given no annotations, no output schema, and a nested spec object at 0% schema coverage, the description is thorough about spec internals, output artifacts, and rerun behavior. It still leaves an agent without guidance on the 'out' parameter or on how a finished background job is collected.

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 compensate, and it does: every key of the required nested spec (name, base, simulation_id, scenarios/overrides, seeds, steps) is enumerated and given meaning, with base explicitly typed as a market_test config. The optional 'out' parameter is never mentioned, which is the one real gap.

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/resource: a study runner that crosses several scenarios with several seeds over the same simulated people and yields 'one defended conclusion.' It distinguishes itself from the single-run sibling by defining base as 'a market_test config object,' but it never explicitly contrasts with market_test, run_test, or predict.

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?

'Background job' implies polling via job_status and 'Finished cells are reused on rerun' implies resumability, so usage is inferable. However, there is no explicit when-to-use-this-vs-market_test guidance, no statement of prerequisites, and no exclusion of alternatives.

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