Run a package in Perch

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

With no annotations, the description must disclose behavioral traits. It explains the side effect (launches an external application) and the effect on the widget, but does not describe what happens after launch (e.g., blocking vs. async, return values, error behavior). It also doesn't mention any required prerequisites beyond the environment variable. This is a moderate disclosure—adequate for a launcher but missing potential status/output details.

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 sentences with no redundant words. The main action is front-loaded ('Launches Perch...'), followed by the effect, platform constraint, and environment variable tip. Every sentence carries meaningful information, making it highly efficient.

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 simple launcher with one param and no output schema, the description covers the essential details: what it does, platform, environment setup, and expected effect. It lacks explicit mention of return behavior or post-launch outcomes, but given the simplicity and the absence of annotations, it is reasonably complete. Siblings are clearly different, so no additional disambiguation is needed.

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?

The schema already describes the single parameter (package_dir: 'Absolute path of the package folder') with 100% coverage, so the description adds little semantics beyond rephrasing it as 'folder that contains this package.' Since the schema fully documents the parameter, the description doesn't need to add more; 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 action: 'Launches Perch with PERCH_MOD_DEV pointed at the folder...' and names the specific resource (the package folder). It distinguishes the tool from siblings by focusing on execution (run) versus documentation/validation (perch_guide, perch_validate, etc.), and even describes the observable effect (widget appears in Settings → Layout → Widgets and on the notch). Purpose is unambiguous.

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?

The description provides clear context for when to use this tool (to run a package) and includes important platform constraints ('Windows only') and environment setup ('Set PERCH_EXE if Perch is not installed through Steam'). It does not explicitly state when not to use it or mention alternatives (like perch_validate), but the sibling tools are clearly different in nature, so the usage intent is inferable without explicit exclusions.

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