Validate the model

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

With no annotations, the description carries the full burden and does most of it: 'static audit' signals a non-mutating read, and it discloses the return shape (score plus findings) and the specific finding categories. It never explicitly states that the project is left unmodified or how the score is computed, so a 4 rather than a 5.

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, purpose front-loaded, and the long check list is dense but each item earns its place by telling the agent what a finding can mean. Slightly list-heavy, but no filler.

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?

No output schema exists, so the description must supply return semantics, and it does ('a score plus findings' plus the finding taxonomy). Given zero parameters and no annotations, the main remaining gap is that the score's scale/meaning is not described.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The enumerated check categories serve as useful output semantics rather than parameter semantics.

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?

States a specific verb and resource ('Run a static audit of the project') and enumerates exactly what it inspects, so an agent knows this is the model-quality checker rather than a general file or element tool. It does not explicitly differentiate itself from the similarly named sibling 'bb_review', which would have pushed this to a 5.

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?

'Fix and re-run before declaring a model finished' gives a clear trigger context for invocation as a final QA gate. It offers no explicit when-not guidance or named alternatives (e.g., bb_review), so it stops short of a 5.

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