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

With no annotations at all, the description carries the full burden and does substantial work: it flags deprecation, discloses the platform-admin requirement for cross-org access, marks `set` as a write, explains that `from_version` restores prior state, and warns that `delete` drops history permanently. What it omits is what `set` does to unspecified fields and what any op returns, so the mutation semantics are only partly covered.

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 deprecation and the admin/cross-org constraint are front-loaded, and the op breakdown is compressed into a single dense line with no filler sentences. The slash-delimited op syntax is terse to the point of being hard to parse on first read, but every clause carries information.

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 15-parameter, four-operation write-and-delete tool with no annotations and no output schema, the description covers the decision-critical surface (access requirement, op selection, destructive delete, restore path) but leaves a large fraction of parameters and all return shapes undescribed. An agent could call the common paths correctly yet still mis-set `full`, `verbose`, `version` or `with_history`.

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 0% across 15 parameters, so the description must compensate and it only partly does. It gives real meaning for `op`, `slug` (three distinct behaviors: one skill, none = base+index, exact slug for delete), `scope=group`, `from_version` (restore) and `slots` (required entities, ADR 0035) — the params that actually discriminate behavior. Nine parameters, including `full`, `verbose`, `query`, `version`, `with_history`, `body_md`, `title`, `description` and `_org`, receive no explanation anywhere.

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 names the resource precisely ('Another org's guide, by `org_id`') and enumerates the four operations (get/list/set/delete), so an agent knows this is a CRUD surface over a tenant-scoped guide document. The deprecation line and the pointer to `oto_admin_guide` distinguish it from its nearest sibling. It falls short of 5 only because the top-line framing is buried behind the deprecation notice and the multi-op nature means no single verb anchors the tool.

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 explicit migration guidance ('utilisez `oto_admin_guide`', removal date 30/11/2026) and a prerequisite ('cross-org = platform admin'), which is exactly the kind of routing an agent needs. Per-op conditions are also sketched (omit slug = base, `scope=group`, exact slug for delete). There are no explicit when-not-to-use statements beyond the deprecation, which keeps it from a 5.

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