run_scenarios

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

With no annotations, the description carries full burden. It discloses that the original cell formula is captured and restored after the sweep (even on error), leaving the workbook in its pre-call state. It also notes each scenario takes roughly the same time as run_simulation. Missing details on potential side effects or blocking behavior, but the recovery disclosure is strong.

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?

The description is a single paragraph of about 4 sentences, efficiently conveying the core function and key behavioral points. It is front-loaded with the main action and purpose. While not structured with bullets, it is clear and compact.

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 the tool's complexity (scenario sweeping, cell restoration) and the presence of an output schema, the description covers the main behavioral aspects: what it does, time cost, recovery guarantee. It does not explain whether results are returned synchronously or how errors beyond restoration are handled, but it is largely complete for an agent to decide when to use it.

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%, so the schema already documents all 6 parameters. The description adds a small guideline (3-7 scenarios) but does not significantly expand on parameter meaning, format, or constraints beyond what the schema provides. Baseline 3 is appropriate.

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 clearly states the tool's action: sweeping a single input cell across multiple deterministic values, running simulations, and returning per-output statistics. It distinguishes itself from sibling run_simulation by explicitly describing the scenario-sweep nature and gives a concrete what-if example.

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 provides usage context: useful for what-if analysis and suggests keeping the values list short (3-7 scenarios) due to time cost per scenario. It implies not for single simulations, but does not explicitly compare to alternatives like run_simulation or propose_distributions_for_inputs.

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