send_message

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

No annotations are provided, so the description carries the full burden for behavioral disclosure. It does reveal that msg_type accepts specific values, provides example content_json structures for common types, and explains agent_id's default behavior. However, it does not disclose potential side effects (e.g., message delivery may fail silently), any authentication/permission requirements, rate limits, or what happens if no recipients are specified. The disclosed information is helpful but incomplete for a state-changing operation.

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 concise and relatively well-structured, starting with a one-line purpose then an Args section with parameter definitions and examples. It avoids unnecessary verbosity and front-loads the core purpose. However, the parameter documentation is somewhat dense and not uniformly formatted, slightly reducing readability.

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?

Given the tool's complexity (6 parameters, no annotations, generic purpose), the description is incomplete. It fails to explain three of the six parameters (to_user, to_party, to_tag) which are crucial for directing a message. It also lacks guidance on whether at least one recipient is required and how multiple recipients are specified. The output schema reduces the need for return-value details, but the missing recipient semantics are a critical gap in context.

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?

The input schema only provides titles and defaults for six parameters, with no descriptions. The tool description adds meaning for msg_type (list of allowed values), content_json (with examples for text, markdown, and textcard), and agent_id (purpose and default behavior). However, it completely omits semantics for to_user, to_party, and to_tag, which are essential recipient fields. Thus, it partially compensates for the schema's lack of descriptions but leaves significant gaps.

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 '发送任意类型应用消息 (通用接口)' meaning 'Send any type of application message (generic interface)'. This uses a specific verb (send), a clear resource (application message), and explicitly labels itself as a generic interface, which differentiates it from sibling tools like send_text_message and send_markdown_message that handle specific message types.

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 indicates this is a generic interface for any message type, which strongly implies it should be used when specialized send tools (e.g., send_text_message, send_markdown_message) are insufficient or when dealing with less common types like news or template_card. However, it does not explicitly state when not to use it or name alternatives, missing a fully explicit exclusion. The context is clear but not fully explicit.

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