run

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

Annotations already declare destructive=true, openWorld=true, non-idempotent, and non-read-only, so the safety profile is covered. The description adds genuinely new context beyond that: the requirement for a trusted owner and an interactive Windows x64 desktop, which are real preconditions an agent must satisfy before calling.

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?

Two short sentences with zero filler, and the platform/precondition framing comes first. It is appropriately sized, though the opening 'Windows AutoIt run' is clipped rather than a clean statement of purpose.

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 destructive, open-world execution tool with several near-identical siblings, the description is thin: it does not say whether the call blocks or returns a handle, what result (if any) comes back, or how it relates to runWait/runAs. It covers prerequisites but leaves the run-variant distinction and return behavior 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 description coverage is 100%, so program, showFlag, and workingDir are already documented in the schema. The description adds no syntax, format, or interaction detail beyond that, so the baseline 3 for schema-driven parameters 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 phrase 'Windows AutoIt run' plus the required 'program' parameter implies the tool launches an executable or command on Windows, so the purpose is inferable. However, it never states the verb+object plainly (e.g. 'executes a program') and gives no indication of how it differs from sibling 'runWait', 'runAs', or 'runAsWait'.

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?

There is no when-to-use guidance and no mention of alternatives, even though the sibling set contains runWait, runAs, and runAsWait, which encode meaningful scheduling and identity choices. An agent gets no help deciding which 'run' variant to pick.

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