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

Annotations only say non-read-only, destructive and idempotent; the description goes well beyond that by disclosing the pin cap with a 403 failure mode, the no-op on an already-pinned version, the fact that restore overwrites live items/schema/inputs after writing a `restore` backup, the `backup_version_id: null` edge case, and the read-only-key visibility rule.

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?

Dense but front-loaded: the target and op come first, then per-op semantics, then return shapes. Every sentence carries information, though the run-on packing of return fields is slightly hard 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?

For a destructive, nested-parameter mutation with no output schema, the description is complete: it covers targeting rules, per-op side effects, error conditions (403 cap), required inputs, visibility, and both return shapes. An agent has everything needed to invoke it correctly.

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 already 100%, so the baseline is 3. The description still adds value by tying conditional requirements to ops (`summary` only with `restore`, `version` being exactly one identifier form) and by explaining that `model_id` is validated against a bound model for model-scoped keys, which clarifies requiredness beyond the schema text.

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 set (pin/unpin/restore) acting on a precisely scoped resource (one version of a model) and names the three mutually exclusive identifiers accepted. No sibling tool overlaps, and an agent can distinguish this from layerz_history, layerz_diff or layerz_get_model without opening the schema.

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?

Each `op` is given a clear effect and condition: `pin` for retaining beyond the history window, `unpin` to free the slot, `restore` to roll live state back (with `summary` mandatory). It also states the target must be in-window or pinned and that the tool is hidden from read-only keys. It stops short of an explicit when-to-prefer-this-over-alternatives statement, but per-op semantics effectively cover selection.

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