bootstrap

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

With no annotations provided, the description discloses key behaviors: generates specific files, does not overwrite without force, and returns setup instructions. There is slight ambiguity about the 'onboarding interview' process (assumed automatic), but overall it's transparent about side effects and conditions.

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?

Two sentences efficiently convey the purpose, generated artifacts, conditional behavior, and return value. No redundant words or fluff, earning a perfect score.

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 covers the main workflow and key behavior (no overwrite unless force). However, it does not detail the return format of 'setup instructions' or specify error handling for existing files without force. Given the absence of an output schema, slightly more detail could be useful, but it's sufficient for a bootstrap 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%, so the description adds no extra meaning beyond what the schema already provides for each parameter. The description mentions the files generated but does not elaborate on how parameters influence the output, which is fine given the schema completeness.

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 the tool initializes a new loom identity from scratch, listing the specific files generated (IDENTITY.md, preferences.md, self-model.md) and the return of setup instructions. This distinguishes it from sibling tools like 'identity' (likely read) and 'update_identity' (modify).

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 implies it's for initial creation by saying 'from scratch' and specifies it won't overwrite existing files unless force is true, giving context on when to use the force parameter. It lacks explicit mention of alternatives or when not to use, but the context is clear enough for an agent.

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