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

Annotations already declare destructiveHint=true, openWorldHint=true, and idempotentHint=false, but the description adds real value beyond that: it discloses atomic association of the providerPatient ID, that history is retained, and four specific effects the call will never trigger. That negative-effect enumeration is genuinely useful for a destructive write. It doesn't mention the idempotency_key parameter or what a revision conflict produces, which is a notable omission given idempotentHint=false.

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 with the core action front-loaded and the constraints following. The never-list is information-dense rather than wasteful, though the opening sentence is repetitive with the title and could be tightened.

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 mutation with no output schema and near-zero parameter documentation, the description covers scope and side-effect boundaries but leaves critical gaps: what happens on revision mismatch, whether the call returns the new revision, how conflicts should be retried with the idempotency_key, and what the contacts array constraints mean in practice.

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?

With only 11% schema description coverage across 9 parameters (7 required) and nested objects, the description carries the burden of explaining parameters, and it only gestures at providerPatient ('Optionally associate a sourced Bask providerPatient ID atomically') and sourceReference ('source evidence'). It says nothing about expectedRevision's optimistic-concurrency semantics, the contacts array structure, environment, or displayName, leaving most of the schema's undocumented parameters unexplained.

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 a specific verb and resource ('Save an owned administrative customer and contact discovery leads with source evidence at an expected revision'), which distinguishes it from the read-only sibling summer_customers_search. However, the phrasing is dense and idiosyncratic ('owned administrative customer,' 'discovery leads'), so an agent must parse jargon rather than recognize a familiar operation, and it doesn't explicitly name the sibling it differs from.

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 states a clear prerequisite ('Company admin required') and defines the tool's boundaries through explicit exclusions ('never verifies a patient, links a sign-in session, enables a provider or authorizes a customer effect'). What's missing is direct routing guidance to alternatives — it doesn't say when to use this versus summer_customers_search or summer_messenger_leads_list, nor what conditions make a save appropriate.

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