shortcut_build

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

No annotations are provided, so the description carries the full burden and does substantial work: it discloses the write artifact (.shortcut file), the platform constraint on signing (macOS), the lint-pass behavior with 'fix all errors' guidance, and the return payload (paths, action count, lint findings). It stops short of covering overwrite behavior on an existing output_path or any credential requirements for signing.

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?

Four short sentences, front-loaded with the core action and the spec shape, then reference pointer, then signing condition, then return values. Only blemish is a stray line break mid-sentence that slightly fragments the second thought; there is 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?

Returns are described, which compensates for the absent output schema, and the required spec parameter is illustrated. But for a mutating build tool with 0% schema coverage and no annotations, the missing semantics for sign_mode and output_path plus the lack of overwrite/error behavior leave real gaps.

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 0%, so the description must compensate; it explains the required spec object's top-level keys and the sign flag's macOS condition. However, sign_mode (a free-form string defaulting to "anyone" with no enum or description) and output_path are left entirely undefined, which is a meaningful gap on a signing-related 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?

Specific verb+resource: builds a .shortcut file from a JSON spec and lints it, with the spec shape sketched inline ({"name": ..., "actions": [...]}). An agent can distinguish it from shortcut_lint or shortcut_sign, though the fact that linting is bundled here (rather than deferring to the sibling shortcut_lint) is only implicit.

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 real conditional guidance: set sign=true on macOS for an importable signed file, and consult shortcut_reference(topic="spec") for step types. It does not say when to choose this over shortcut_from_template or the standalone shortcut_lint/shortcut_sign siblings, so no exclusions are stated.

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