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

Adds real context beyond the annotations: the authorization requirement and the effect boundary (no carrier or clinical changes). Annotations already declare destructiveHint=true and openWorldHint=true, so the bar is lower, but the description still doesn't say what the write overwrites (whether the previous shipping address is replaced or retained) or how the live call/order linkage behaves.

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?

Two sentences, front-loaded with the action and object, followed by prerequisites and boundaries. No wasted clauses; every sentence carries distinct 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?

Covers authorization, scope limits, and escalation routing, which is a solid base for a destructive mutation with no output schema. Gaps remain: no statement of the success result, whether the prior address is overwritten, or how idempotency_key should be used (especially given idempotentHint=false alongside a schema-provided retry key).

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 17% across 6 parameters with a nested address object, so the description must compensate but supplies no field-level guidance for caseId, call_id, company, environment, or the address sub-fields. The mention of "confirmed" hints at the address.confirmed flag, but that constant is already enforced by the schema, adding no new meaning.

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 ("Save") and a tightly scoped resource: a confirmed administrative shipping-address correction for the selected order on a live outbound pharmacy call. This distinguishes it from the address-unrelated siblings (summer_pharmacy_calls_settings_update, summer_cases_assignment_update) without needing to open 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?

Gives a prerequisite (Ops admin plus customer-effect access) and explicit exclusions (carriers, clinical fields), plus a routing rule for out-of-scope cases (cross-state → clinical coverage review). An agent knows both when this tool applies and where to send requests it must not handle.

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