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

Beyond the readOnlyHint annotation, it discloses that the write path auto-repairs some issues (dangling source_uid/inputs), that certain invariants are only enforced at write (parent_uid), and that the report contains per-issue codes, messages, and item_uids. This is substantial behavioral context and contradicts nothing in the 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?

Although long, every sentence earns its place: purpose, then critical limitations, then output format, then usage recommendation. The most decision-relevant fact (read-only sanity check) is front-loaded, and the structure makes it easy to scan.

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, but the description explicitly defines the return structure ({ ok, error_count, warning_count, errors[], warnings[] }) and the error sub-fields. It also covers when to use, what it does, and its limitations—nothing an agent needs to call it correctly is missing.

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 schema already provides 100% coverage of model_id, including format, requiredness per key type, and scope behavior. The description adds no parameter-specific meaning, so the baseline of 3 applies.

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 opens with a precise verb-resource pair ('Audit a model without writing') and enumerates the exact checks (structural / formula / timeline). It explicitly contrasts with the write path, so an agent can distinguish this from layerz_patch or layerz_create_model without opening their schemas.

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 an explicit recommendation ('use it as an agent-side sanity check before sharing') and clearly states what it is NOT (a byte-for-byte write preview) and why ok:true is insufficient to guarantee a write. This frames both when to call and when to avoid relying on it.

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