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

Beyond the write, destructive, and open-world annotations, it discloses irreversibility, refusal when blocked, request-style delivery to strangers, a possible profile-photo prerequisite, and behavior when a conversation already exists. These details substantially help the agent anticipate side effects and failures, and none contradict 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 purpose and irreversibility warning are front-loaded, and the remaining sentences contain actionable selection or behavioral details. The required-input sentence is somewhat redundant with the schema, and the semicolon-heavy sentence compresses three separate edge cases densely.

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 side-effecting messaging tool with no output schema, it covers the key prerequisites, delivery behavior, failure condition, irreversibility, and conversation routing needed for correct invocation. It does not describe the success result, and the mismatched reply-tool reference prevents the definition from being fully self-contained.

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 100%, and the description largely reiterates the documented recipient id and message-text requirements. It adds little parameter-specific meaning for person, dry_run, or project beyond what the schema already supplies.

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 gives a specific action, resource, actor, and scope: sending a first Connections message as the member to exactly one person. This clearly distinguishes it from reading messages or replying to an existing inbox conversation.

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?

It explains when to use the tool, cautions to send only member-requested text, clarifies that an existing conversation still receives the message, and redirects inbox replies elsewhere. However, the named alternative, reply_to_conversation, is absent from the supplied siblings, where connections_message_reply appears to be the corresponding tool, making that routing less reliable.

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