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

Annotations declare readOnlyHint=false but leave the mutation unspecified; the description fills that in by naming the writes (annotations to the schema), the billing implication, the incremental-vs-full execution model, and the error condition. It also explicitly bounds scope — suggested structural changes are not applied, they come back as pending proposals — which prevents an agent from assuming edits landed.

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?

Front-loaded with purpose and side effect, then progressively narrower operational facts; every sentence carries distinct information. It is dense telegraphic prose ('Requires editor; billed.') that is efficient but verges on terse jargon with terms like 'identity scoping' and 'unification proposals' left unexplained.

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?

An output schema exists, yet the description still sketches the return payload (findings, suggested descriptions, identity-scoping annotations, pending proposals), which is the piece an agent most needs to chain this into review/approval steps. Combined with role requirements, billing, error mode and the docs URI, nothing material 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?

Schema coverage is 100%, so the baseline would be 3, but the description adds real semantics for force ('rechecks all sites' vs incremental default) that the schema only phrases as 're-analyze every property'. The model parameter is left entirely to its schema description.

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 plus the exact scope: property ambiguity and relationship identity scoping on a saved schema, with the side effect of writing annotations. That distinguishes it from get_schema (read-only retrieval), update_schema_property (per-property edits), and publish_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?

Gives concrete operating guidance: requires editor role, is billed, incremental by default, force=true to recheck everything, and fails with ambiguity_check_disabled when the feature is off. It also routes to update_schema_property for approved descriptions or renames. What's missing is the triggering condition in the workflow — nothing says when in the schema lifecycle to call this rather than after save_schema or before publish_schema.

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