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

With no annotations, the description does real work: it discloses that the reply comes from the agent's current script, that no real contact occurs, and that a script must exist first. It does not mention credit consumption or whether the test affects agent state, which are the remaining unknowns for a dry-run 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?

Three short clauses, zero filler, with the no-contact safety assurance placed early. Every sentence carries actionable information.

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 3-param dry-run tool with no output schema, the description covers the prerequisite, the side-effect profile, and the multi-turn mechanism. Only the shape of the reply and any cost implication are left implicit.

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 100%, so id, message and history are already documented. The description only adds that history is what enables a multi-turn test, which is a marginal restatement of the schema's "Earlier turns, oldest first".

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 a message to the agent, get its reply) and immediately scopes it as a text test that contacts nobody, which cleanly separates it from the phone/call testing siblings. An agent can pick this over phone_test_call 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?

Gives a hard prerequisite ("Needs a generated script") and a conditional steering rule ("Use history for a multi-turn test"). It stops short of naming the phone alternative explicitly, so the text-vs-voice routing is implied rather than stated.

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