messages_send

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

No annotations are provided, so the description carries the full behavioral burden. It says 'immediately', which implies direct dispatch without scheduling, but does not disclose rate limits, whether sends are irreversible, whether audience and broadcast interact (broadcast=true vs audience/segment_id), subscription-state effects, or any error behavior for a 12-parameter high-impact send tool.

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?

A single front-loaded sentence with no filler. It is appropriately sized for what little it says, though the brevity contributes to the other gaps rather than compensating for them.

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 12-parameter, nested-object, no-annotation, no-output-schema send tool with many overlapping siblings, the description is inadequate. It omits recipient targeting semantics, channel selection guidance, prerequisites (apiKey, restEndpoint), and behavioral caveats that an agent needs before invoking a synchronous send.

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 67% and the description does not explain any of the 12 parameters. Key semantics are left ambiguous: how 'broadcast', 'audience', 'segment_id', 'external_user_ids', and 'user_aliases' interact to define the recipient set, or how 'messages' channel keys map to 'recipient_subscription_state'. The description adds no parameter meaning beyond what partial schema descriptions already provide.

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 states the verb (send) and resource (messages) plus the channels, which is clear enough. However, it doesn't distinguish this from close siblings like campaigns_trigger_send, canvas_trigger_send, transactional_email_send, or messages_schedule_create, which all send messages through different mechanisms. A 'one-sentence summary' that covers four channels without naming when this tool is the right one leaves the tool's identity ambiguous among many senders.

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?

No guidance on when to use this tool versus alternatives. With siblings like campaigns_trigger_send, canvas_trigger_send, transactional_email_send, and messages_schedule_create, the agent gets nothing to help choose, and the description does not even hint at the immediate-vs-scheduled distinction that the word 'immediately' implies exists.

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