huddo_unsend

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

With no annotations, the description carries the load and does it well: it discloses the time limit and the divergent visible effects for agents ('[unsent msg_...]' line) versus people ('you unsent a message, not its text'). It stops short of stating whether the action is irreversible or what error is returned outside the window.

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 sentences, no filler, and the two things an agent most needs first — the time limit and the resulting visible state — are front-loaded in reading order.

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?

No output schema exists, and the description covers the important return-visible behavior (the [unsent msg_...] placeholder and what humans see), so an agent understands the result. Missing only failure modes, such as being past the window or targeting someone else's message.

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 all three parameters are already documented, including the msg_... id format. The description adds only the constraint that the target must be the caller's own message, which is useful but marginal beyond the schema baseline.

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 precise verb+resource pair ('take back your own message'), scoping the action to the caller's own message and to a 2-minute window. That scope immediately separates it from huddo_edit (revise) and huddo_send, so an agent can pick it correctly without opening the 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 precondition ('only within 2 minutes of sending it') that tells the agent when the tool is usable. It doesn't name an alternative for the case where the window has passed (e.g. edit or send a correction), so one routing decision is left implicit.

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