Delimit Generate Scaffold

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

Annotations only say readOnlyHint=false and destructiveHint=false, so the description carries the burden of explaining mutation behavior. It does this thoroughly: writes MANY files, uses backends.generate_bridge.scaffold, coerces packages via _coerce_list_arg with short-circuit on malformed values, has no license gate, no ledger write, no notification, and leaves collision behavior to the backend. This is exactly the operational context an agent needs beyond the annotations.

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?

The description is long but every section earns its place: purpose, when to use, when not to use, sibling contrast, and side effects. The labeled sections make it easy to scan, and the critical caveat about collision behavior is placed at the end as a warning. No filler or repetition of schema fields.

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 tool that writes many files and has minimal annotations, the description is fully complete: it specifies target state, exact non-uses, sibling alternative, side effects, follow-up step, and collision caveat. Since an output schema is present, the lack of return-value documentation is acceptable. The agent can safely decide whether and how to invoke this tool.

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 provides 100% parameter descriptions, so the baseline is 3. The description adds genuine extra meaning: packages is coerced from a comma string into a list and malformed values short-circuit, which is not stated in the schema. It also reinforces that name becomes the root directory and gives concrete example values for project_type.

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 opens with a specific verb and resource: 'Lay out a fresh project tree with framework-conformant skeleton.' It clearly distinguishes this tool from its closest sibling, delimit_generate_template, by contrasting 'writes a NEW project tree' with 'writes a single file into an existing project.' The intended project types (Next.js app, API service, library) are named explicitly.

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 has explicit 'When to use' and 'When NOT to use' sections. It names alternative tools and strategies: delimit_generate_template for single-file scaffolds, the shell for duplicating projects, and the project's own package manager for adding packages. It also identifies the typical follow-up tool, delimit_init, so an agent knows the surrounding workflow.

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