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

Going well beyond the openWorldHint/destructiveHint annotations, the description discloses irreversible and conditional behaviors: international numbers are delivered one-way via an alphanumeric sender ID with 'no error returned,' messages are screened after payment, 'held messages and calls are not sent,' refunds are not immediate, and answering a call does not establish consent. It also surfaces data-retention windows and de-identification caveats. Nothing contradicts the annotations.

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 core purpose, payment requirement, and matching constraint are efficiently front-loaded in the first few sentences. However, the back half becomes a near-privacy-policy (appeal costs, 24-hour context records, 30-day cleanup, de-identification limits) that is far more verbose than needed for an agent to select and invoke the tool correctly; it could be condensed significantly without losing invocation-relevant guidance.

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, world-facing tool with no output schema, the description covers the payment prerequisite, delivery caveats, screening/hold behavior, refund rules, consent constraints, and data handling. The main gap is the lack of any description of the return value or how to confirm the send outcome (e.g., via check_payment_status), though no output schema exists to fill that void.

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 parameter basics are already documented, giving a baseline of 3. The description adds critical cross-tool semantics not in the schema: phoneNumber and message 'must match those used in create_payment,' and the billed segment count includes an appended signature line plus safety/stop link. This is meaningful value beyond the structured fields.

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 opening sentence, 'Reach a human via SMS when your task requires real-world coordination,' names a specific verb, channel, and purpose, and the claim of sending to 'any phone number worldwide' differentiates it from siblings like send_email, send_fax, and place_call. The tool's resource (SMS to a phone) is unambiguous, with no confusion about what it is for.

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?

'When your task requires real-world coordination' supplies a clear trigger condition, and the explicit prerequisite — 'Requires create_payment with toolName='send_sms' and phoneNumber+message at payment time' — gives a concrete preconditions. However, no sibling tool is named and there is no explicit 'use send_email instead when...' exclusion, so alternative routing 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.