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

Annotations only convey non-read-only, non-idempotent, non-destructive flags. The description adds valuable behavior: it returns a new spec_text and reopens the scope, requiring a follow-up accept. This is meaningful transparency beyond the structured 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 two sentences, front-loaded with the core action and output, then the lifecycle constraint. The 'Build it Better: BB-CHANGE' prefix is somewhat redundant with the title, but the rest is compact and purposeful.

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 mutating workflow tool with no output schema, it covers what it returns, when it can be used, and the important side effect of reopening the scope. Remaining details like request_token consumption are already present in the schema.

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% and each parameter already has a meaningful description. The tool description adds little parameter-specific detail, so the schema carries the burden, making the baseline score of 3 appropriate.

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 action ('ask for a scope change') and the returned artifact ('new spec_text'), and grounds it in the BB accept/build lifecycle. This makes it easy to distinguish from sibling BB tools like bb_accept_spec and bb_file_request.

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?

It gives actionable timing guidance: usable before accepting, and after BB-ACCEPT until the build starts, followed by the note that the scope reopens and must be accepted again. It does not explicitly name the sibling tool for re-accepting, but the lifecycle context is clear enough.

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