run_analysis

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

With no annotations, the description carries the full burden. It does disclose substantive behavior: the step grammar (set/call/run/result/saveGraph), that results come back as tables, arrays or document handles, and which image formats saveGraph supports. It is silent on whether a run mutates the source spreadsheet, what happens on a failing step, and whether steps are atomic — meaningful gaps for a tool that executes arbitrary dialog operations.

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 the purpose, then the step grammar, then the routing hint to describe_analysis. Dense but every clause is functional; the parenthetical examples and extension list all carry information. No filler sentences.

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?

There is no output schema, and the description compensates by stating the return forms (tables, arrays, document handles). Combined with the step grammar and the describe_analysis pointer, an agent has enough to construct a call. Only error/failure semantics and the mutation footprint of a run are left unaddressed.

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 83%, so the schema already documents most parameters. The description goes well beyond it for the critical 'steps' array, spelling out each step type and giving concrete examples (set/call/run/result/saveGraph) that the schema's one-line example does not, which is exactly the kind of added meaning that matters for the hardest parameter.

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 and resource ('Run ANY STATISTICA analysis') plus the mechanism ('executing an ordered list of steps against its dialog'). The word 'ANY' implicitly differentiates it from the specialized siblings (statistica_regression, statistica_t_test, statistica_anova), but it never names them, so the agent must infer the routing rule.

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 directs the agent to describe_analysis for discovering property and method names, which is genuinely useful workflow guidance. However, it never says when to prefer this generic runner over the many pre-built analysis siblings, nor when-not to use it, so selection remains implied rather than stated.

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