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

With no annotations, the description carries the full burden. It reveals the timeout behavior (max 25s), the trust warning, and the encryption alternative. However, it does not disclose what the tool returns on success, failure, or timeout, nor does it explain how the wait works (e.g., blocking vs non-blocking). This is a significant gap for a tool with no output schema.

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 three concise sentences, front-loading the primary action and then adding usage context and security guidance. It avoids redundancy and keeps each sentence purposeful. The structure is efficient, though it could be slightly clearer about the return behavior.

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 (8 parameters, nested objects, no output schema, no annotations), the description is insufficient. It omits critical information about the return value, timeout handling when no reply is received, error conditions, and the semantics of parts, token, and expect_reply. An agent would likely need additional documentation to invoke this correctly in edge cases.

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 only 38%, and the description compensates for the critical envelope vs. text distinction, explaining when to use each. It also indirectly defines wait_seconds via the max 25s statement. However, it does not clarify the meaning or usage of parts, token, expect_reply, or the relationship between text and parts, leaving these to the sparse schema.

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 clearly states the action: send a message and wait for a reply, with a maximum wait time. It identifies this as 'the realtime tool,' which distinguishes it from asynchronous siblings like send_message, though it doesn't explicitly name alternatives. The verb-resource combination is specific and unambiguous.

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 explicitly instructs to use this tool when the owner asks to talk to another agent, and it notes the realtime nature. It also provides guidance on the security context (peer text untrusted, use envelope when a public key exists), which informs when to pass envelope versus text. However, it does not explicitly state when NOT to use it or name specific alternatives.

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