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

With no annotations, the description carries real behavioral weight: rate limit (≤30/hour/key → 429), tenant-scoped effects with no cross-tenant impact, raw media staying on the caller's side, durable audit trail, and the caveat that it is not a legal deletion SLA. It does not clarify the return shape or whether the operation is idempotent, but the safety-relevant disclosure is strong.

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?

'Privacy-first erasure', 'durable audit', and 'not a legal deletion SLA' are each stated twice across the two paragraphs, and the second paragraph largely restates the first. The trailing 'List: GET /v1/pbx/redact/audit' is also meta-information for a sibling tool rather than this one, so the text is longer than it needs to be.

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 annotations and no output schema, the description covers scope, rate limits, and audit behavior but omits what the call returns and the key input constraint (target_id or phone required). An agent has enough to be cautious but not enough to predict the response.

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 100%, so the schema already documents mode, target_id, phone, target_type, who, and reason. The description only echoes mode semantics and the target_id/phone lookup, adding no constraint such as the required at-least-one-of selection. Baseline 3 applies when the schema does the heavy lifting.

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+resource (privacy-first erasure / clearing a derived index by id or phone) and names the exact data it touches (Person/Promise/Fact/partial index + audio pointers). It also distinguishes itself from the sibling pbx_redact_audit by pointing to the audit listing route. An agent can identify this as the destructive redaction tool without opening the 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?

Implies usage through 'Lookup by target_id or phone' and mentions the audit endpoint, but never states when to choose this over pbx_redact_audit or other pbx tools, nor does it state the prerequisite that at least one of target_id/phone is needed despite 0 required params. Guidance is inferable but not explicit.

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