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

Annotations already declare a destructive, non-idempotent, open-world write, and the description adds two facts the annotations cannot convey: a stale version is refused (optimistic concurrency) and previous values persist on an audit row, which softens the destructive hint. It stops short of permissions, failure/partial-write behavior, or the waitlist fallback.

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?

Five short sentences with the core action and required inputs front-loaded; nothing is padded. The field-type sentence is slightly elliptical in phrasing ('said in ordinary words'), which costs a little clarity.

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 six-parameter mutation with a nested data object and no output schema, the description covers the concurrency contract, audit retention, and the main routing decision. Remaining gaps are the waitlist fallback and any statement about what a successful update returns.

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 is 3, but the description adds real meaning: data keys are column names (with 'Phone number' as an example), and id plus the current version must be sent together. The waitlist parameter is left entirely to the schema.

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 a narrow scope: 'Changes one stored person after crm_query.' It also explicitly separates itself from crm_define_model, so an agent can route between the two without opening either 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 both a prerequisite ('after crm_query') and an explicit when-not with the alternative named (field-type definitions belong to crm_define_model). It does not cover other plausible confusions, such as crm_create vs crm_update or when to prefer crm_delete.

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