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

With no annotations, the description carries the full burden and does so: it enumerates exactly what is destroyed (contact, activity history, recordings, transcripts, outcomes, numbers, action/handoff content) versus retained (time, status, duration, cost), states the operation is permanent, and defines preconditions (no active call, no unresolved action). The doNotCall fingerprint semantics — one-way, prevents future calls/answers, always kept after opt-out — are disclosed rather than hidden.

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?

Three dense sentences, front-loaded with the action and its destructiveness before the caveats. Given this is an irreversible destructive operation, every clause (refusals, retained fields, doNotCall) earns its place.

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 annotations and no output schema, so the description must supply the entire behavioral contract — and it covers destruction scope, retention, preconditions, irreversibility and the doNotCall side effect. Nothing material an agent needs to invoke this safely 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 75%, so the schema documents most parameters, but the description still adds meaning: it frames id vs destination as an either/or, explains destination covers non-contact inbound callers, and expands doNotCall beyond the schema's one-line note into its actual effect. workspaceId is left unremarked but is self-evident.

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 ('permanently erase one person's personal data') plus the two addressing modes (contact id or phone number/destination) and the edge case of non-contact inbound callers. An agent can distinguish it from contacts_suppress, contacts_update and contacts_export without opening a 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 an explicit use case ('data-subject erasure requests'), an audience constraint ('Admins'), a sequencing directive ('download the audit first if you need to answer an access request'), and the refusal conditions. It stops short of naming the nearest alternative, contacts_suppress, so the choice between erasure and suppression is left to inference.

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