Send a message

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

Goes well past the annotations: it warns that this really sends and spends credit, that suppressed/unsubscribed recipients still get a message id and fail later (read final status via sendkuy_get_messages), that one recipient is sent synchronously while several are queued and paced per number, and that the response counts per status but lists only the first 20 messages. The dedupe_key narrative adds retry-safety semantics the annotations do not capture.

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?

Front-loaded with the verb, channel set and recipient cap, then arranged by concern: alternatives, recipient format, side effects, delivery pacing, idempotency, response shape. Long for a description, but nearly every sentence introduces a new operational fact rather than repeating the schema.

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 mutating, credit-spending, 11-parameter tool with nested objects, the description covers the risks an agent needs: cost, partial-failure visibility, sync vs queued delivery, idempotency, and where to read the remaining results. An output schema exists, so the brief note about the response is a bonus rather than a gap-filler.

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 91%, so the schema carries most parameter meaning, but the description adds operational detail not in the schema: phone numbers must be E.164 with the leading + and a concrete example, and that a grp_ id may be substituted for individual recipients. It still says nothing about media, attachments, schedule_at, template_id or gateway_id, so it does not fully cover the 11-parameter surface.

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 (send one message body), plus the hard scope constraint of 1 to 100 recipients on exactly one of three named channels. It also names what it is not: batch sends with per-recipient content and dashboard campaigns, so an agent can distinguish it from sendkuy_send_batch and sendkuy_start_campaign 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?

Explicit when-to-use (alert, summary, one-off notification where everyone gets the same text), explicit alternative for divergent content (sendkuy_send_batch, with examples of branch/order summaries), and an explicit route for dashboard-prepared campaigns (sendkuy_start_campaign). It even says how to target a saved group by putting its grp_ id in to.

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