Scaffold Project

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

Annotations already carry destructiveHint: true; the description adds useful traits such as 'created if absent' for base_dir and the guarantee that merge_assembly consumes the output unchanged. It stops short of saying what happens to existing files if scaffold_project is run over an existing project, which is the main missing destructive detail.

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 front-loaded with the main action, then parameter semantics, then the return layout, so the structure is easy to scan. It contains some internal references (issue numbers, MULTI_AGENT.md sections) that add specificity but also noise; still, every section earns its place.

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 7-parameter tool with no output schema, the description covers all params and explicitly lists the returned layout keys. It omits edge-case behavior such as overwrite or error handling, but an agent has enough context to call the tool correctly and understand the result.

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?

With 0% schema description coverage, the description carries all parameter meaning and largely succeeds: base_dir, name, master, and items each get a purpose, and components/instances/shared_parameters are identified as 'assembly manifest content.' It groups the manifest payload somewhat loosely and does not specify the exact shapes inside components/instances, but it gives the agent enough to construct a valid call.

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 concrete verb and resource ('Lay out a well-formed project in one call') and enumerates the artifacts created: convention directories, items.json registry, assembly manifest, and project.json. It also positions the tool relative to merge_assembly, which consumes the output unchanged, so an agent can distinguish this from project_validate/resolve_manifest siblings.

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 clearly frames the tool as the one-call primitive for initial project layout and states the resulting project loads clean and is directly consumable by merge_assembly. It does not explicitly list when not to use it or name alternatives, but the context is strong enough to route an agent.

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