bootstrap

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

There are no annotations, so the description carries the behavioral burden. It does disclose that it generates files, requires an interview, does not overwrite unless force is true, and returns setup instructions. It also reveals internal defaults ('everything structural ... is written by the scaffold'). It does not go deeper into side effects such as whether files are created in the current directory, whether the interview is interactive, or whether any external calls occur, but the main behavior is reasonably transparent.

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?

Three sentences, front-loaded with the verb and resource, then deliverables, then an important constraint about the interview and overwrite behavior. Every sentence earns its place and no information is wasted.

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 the core workflow, the interview scope, the generated files, and the overwrite safeguard. It could be more complete by stating where files are written or what 'setup instructions for requested runtimes' looks like, but the essentials an agent needs to act are present.

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 description coverage is 100%, so baseline is 3 even without param info in the description. The description adds useful context by grouping the four interview questions (name, agent name, purpose, voice) and clarifying that 'user' is the human's name rather than the agent's. However, it doesn't elaborate on the clients array's exact allowed values or force semantics beyond what the schema already says. This is acceptable but not exceptional.

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 states a specific verb ('Initialize'), a specific resource ('a new loom identity'), and concrete deliverables (IDENTITY.md, preferences.md, self-model.md). It describes the onboarding-interview source and setup-instruction outputs, and it names a distinguishing behavior relative to siblings (does not overwrite unless force). This is clear and differentiated.

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 implies when to use this tool: when a new loom identity is needed from scratch, and it explicitly warns the agent not to ask structural questions because the scaffold writes them. It does not explicitly name sibling alternatives for when not to use it, but it gives enough context and constraints for an agent to select it appropriately.

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