Run a read-only script

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

Annotations only declare readOnlyHint/openWorldHint, so the description earns credit by disclosing enforcement details: no shell, rejection of absolute paths and `..`, write attempts redirected to run_write, and the return shape (exit code plus trimmed output). This is meaningful beyond the structured fields, though permission/auth requirements and failure semantics are not covered.

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 tight sentences, each earning its place, with the primary action front-loaded and the constraints (no shell, no absolute paths, no writes) following immediately. No filler.

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?

With annotations and an output schema present, the description carries only the behavioral burden it needs to, and it does so well for a read-only execution tool. The one gap is the undefined 'manifest' — an agent is told scripts exist but not where they come from, aside from the built-in list mode.

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 baseline is 3, but the description adds non-obvious semantics the schema does not: omitting `name` triggers listing, and `args` values must be relative without `..`. It still says nothing about `detail`, which the schema carries on its own.

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 ('Runs a read-only script from the manifest') plus the dual mode (run vs. list when name is omitted). It does not explicitly differentiate itself from the siblings `search` and `read`, and 'manifest' is left undefined, but the core action 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?

Gives a clear routing rule against a comparable tool: 'Use it instead of Bash for what a script covers,' and explains the no-argument listing behavior. It stops short of naming the actual siblings (`search`, `read`) or stating when those are preferred over running a script.

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