Group Blueprint Files

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

With no annotations, the description bears full burden. It discloses that prepare is not the final grouping and that apply deterministically assigns files. It does not mention side effects, permissions, or error conditions, but the core behavioral traits are clear.

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 concise and well-structured: two sentences explaining each mode, followed by actionable guidance for the LLM. Every sentence contributes meaning without redundancy.

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?

The description explains prepare mode's return ('compact packet') but omits return behavior for apply mode (e.g., success/failure). No output schema or annotations exist to compensate, making it slightly incomplete for a multi-mode 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?

Schema coverage is 100% with descriptions for all three parameters; the description adds value through usage guidelines for prepare mode (glob patterns, grouping rules) but does not significantly enhance understanding of the parameters themselves beyond the schema.

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 clearly states that the tool has two modes: prepare returns a compact packet for semantic grouping (not final), and apply consumes a GroupingPlan to assign files. It distinguishes the tool's role from siblings like blueprint.scan and blueprint.compose by focusing on grouping.

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 provides explicit guidance for the prepare mode: treat folder names as hints, group by responsibility, prefer glob patterns, use exact paths only for entry points/exceptions. It implies when to use each mode but does not explicitly compare with sibling tools like blueprint.group.update, leaving some gap.

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