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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description adds substantial context beyond them: admin-only authorization, the overwrite semantics affecting all workspace members, that disabling advanced periods never hides existing records, that it touches no external service, and the exact idempotencyKey retry behavior. It also warns that CRM field values are untrusted data, which is real operational context.

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-loads the purpose and scope, then constraints, then the confirmation protocol, so the important material is never buried. The 'Fields: ...' enumeration duplicates schema property names and 'it calls no outside service and sends nothing to anyone' is partly redundant with openWorldHint=false, but the length is defensible for a destructive admin mutation.

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, yet the description covers the safety-critical surface well: authorization, idempotency, cross-field constraint, and a strict confirmation protocol. The notable gap is that 'overwrites' is never disambiguated — it does not say whether omitting an optional field clears it or leaves it unchanged, which an agent needs before calling.

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 only 9%, so the description must carry the load. It does enumerate every commercial field name and supplies one genuinely useful cross-field rule (defaultPriceIntervalMonths must be 1, 3, 6 or 12 unless advancedIntervalsEnabled). However, it never explains what the other fields mean semantically (e.g. what commercialSetupStatus DEFERRED implies, or how primaryCommercialMetric affects behavior), leaving most of the 11 parameters documented only by their enum values.

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 with scope ('Overwrites the workspace's commercial defaults for everyone in it') and enumerates the exact fields it governs. An agent can distinguish it from update_workspace_settings and get_workspace_commercial_settings without opening a schema, and it explicitly carves out the one setting it cannot touch (reporting currency).

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 explicit preconditions ('Only a workspace admin may call it'), an alternative route for the excluded setting ('a workspace admin changes that in the workspace settings'), and a concrete procedural gate: confirm with the user in the same turn, never infer go-ahead from an earlier message or plan, and ask rather than guess. This is unusually complete when-to-use guidance.

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