prepare_poke

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

Beyond the annotations, it discloses the key behavioral fact: nothing is transmitted at call time and delivery is contingent on the recipient approving in their inbox. The 'no arbitrary text or destination' constraint also tells the agent the payload is fixed by the pairing. One caveat: annotations declare destructiveHint=true, which sits in tension with 'Sends nothing', though the tool does create a pending record, so this reads as annotation imprecision rather than a description contradiction.

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?

Two short sentences, zero filler, and the operational fact that most affects agent behavior (nothing is actually sent) is front-loaded right after the action statement.

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 zero-parameter tool with no output schema, the description covers what matters: scope, no send, approval requirement, and fixed payload. It stops short of describing what a successful call returns (e.g., a pending id or confirmation) or whether multiple pending pokes can coexist, which an agent might need.

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?

There are zero parameters, so the baseline is 4. The description does useful work by explaining why the schema is empty — text and destination are deliberately not caller-controlled — which prevents an agent from hunting for optional arguments that do not exist.

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 (prepare) and a specific resource (a plain hello to your mutually paired person), and the target is fully constrained rather than open-ended. The clause 'Sends nothing; user must approve in their inbox' implicitly separates it from send_trusted_message and from read_poke_inbox, so an agent can place it without opening the sibling schemas.

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 establishes context (deferred, approval-gated hello) and rules out misuse with 'No arbitrary text or destination', which implies send_trusted_message is the tool for custom messages. However, it never states an explicit when-to-use condition or names the alternative, so the routing logic is left to inference.

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