update_message

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

Annotations declare a non-readonly, non-destructive mutation, and the description layers on real behavior: delivery time and read-aloud settings are preserved, the edit is visible on the frame immediately, and there are eligibility restrictions. It does not cover failure modes or why the operation is non-idempotent, which keeps it from a 5.

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 primary action is front-loaded in the first sentence, and the following sentences each carry a distinct constraint (eligibility, preserved settings, immediacy, ID source). Slightly verbose across four sentences, but no filler.

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?

With full schema coverage, annotations covering the safety profile, and no output schema, the remaining burden is eligibility and side effects — both addressed. An agent has everything needed to decide whether to call it and how to obtain the message ID.

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 the baseline is 3, and the description adds meaning by naming get_messages as the source of messageId and noting its 31-day lookup range. The 'omit to keep the current sender' semantics for `from` are already in the schema, so no further lift there.

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 ('Edit') and resource ('the text ... of a message already on the frame'), and explicitly covers the optional sender change. This is clearly distinguishable from the sibling send_message, which creates rather than edits.

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?

Spells out the precondition for use ('Only messages sent to everyone on all devices and not repeating can be edited') and the fallback when the condition fails ('anything else must be edited in the Skylight app'). It even routes the agent to get_messages for the required ID, with the 31-day lookup window noted.

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