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

With no annotations, the description carries the full disclosure burden and does so thoroughly. It reveals that numbers are normalized to E.164 before storage because the send-time check is an exact string match, warns that a row in any other shape is silently never found, states that invalid numbers are reported back rather than skipped, and explains the limitation of Twilio suppression. These are critical behavioral traits beyond the schema.

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?

The description is a dense paragraph but every sentence earns its place. It front-loads the purpose, then systematically covers each action, the normalization caveat, error handling, and the Twilio contrast. There is no filler or redundant repetition of schema content; the length is justified by the tool's three-action complexity.

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?

The description covers the essential behavioral context for correct invocation: action semantics, normalization, error reporting, and the relationship to Twilio suppression. However, with no output schema, it leaves minor gaps: it does not state what add/remove return, and it does not mention pagination for list, which could matter for large suppression lists. These are not critical for calling the tool correctly but are the only missing pieces.

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 75% (three of four parameters have descriptions), so the baseline is 3, but the description adds meaningful semantics: it explains what each action value does, the normalization and exact-match behavior for phone/phones, and the context that source labels where an opt-out came from. It does not redundantly repeat schema descriptions but enriches them, especially for action and phone/phones.

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 opens with a specific verb and resource ('Read and maintain the SMS suppression list') and immediately clarifies the account-wide scope. It differentiates the tool from siblings by being the only suppression-list tool among SMS sending and template tools, and it enumerates the three actions (list, add, remove) with distinct semantics.

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?

The description gives explicit conditions for each action: add is for opt-outs that happened elsewhere (before the list existed, on a number no longer owned, or on another platform), remove is only for genuine opt-backs-in, and list returns all suppressed numbers. It explicitly contrasts with Twilio suppression, stating it is NOT a substitute and why, which tells an agent when this tool is the correct choice versus the alternative.

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