Run project script

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

With no annotations provided, the description carries the full burden and does well: it discloses that network is always 'none', execution is confined to a runner-managed READ_WRITE mcp/* worktree, and a non-zero exit code is still a successful MCP call. These are non-obvious and valuable operational details. It omits a few edge behaviors, but the output schema covers return shape.

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?

Three dense sentences, no filler. The most important behavioral constraints are front-loaded, and the surprising exit-code semantics are given their own sentence. Every clause adds decision-relevant information.

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 5-parameter tool with no annotations and no schema descriptions, the description is not fully complete: it lacks parameter-level guidance and explicit routing to project_scripts. However, it does cover environment, network, and exit-code semantics, which are the riskiest aspects of invoking this tool, and an output schema exists for return-value expectations.

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 0%, so the description must compensate, but it only indirectly touches parameters: 'network is always none' clarifies the network parameter, and 'hash-pinned' hints at expectedPackageSha256. It does not explain project, script, timeoutSeconds, or expectedPackageSha256 beyond what the bare schema shows.

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 states a specific action and resource: 'Execute an allowlisted, hash-pinned npm/pnpm script inside a macOS Seatbelt sandbox.' It clearly differentiates run_script from file/git tools and from project_scripts, which likely lists scripts rather than executing them.

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 tool's purpose implies it should be used when a project-defined npm/pnpm script needs to be executed, and the sandbox/network constraints set clear expectations. However, it does not explicitly say when to prefer this over alternatives, nor does it mention project_scripts as the way to discover available allowlisted scripts or what happens for non-allowlisted scripts.

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