Set presence or typing

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

Annotations already declare openWorldHint=true, idempotentHint=true, destructiveHint=false, so safety/idempotency is covered. The description adds behavior beyond them: the lifespan of the typing/recording indicator, the interaction with update_account pacing, and a concrete failure mode ('Fails with not_supported when the account cannot receive presence events'). It stops short of stating whether subscribe persists or how it is undone.

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?

A single front-loaded framing sentence, then a scannable Actions list where each bullet is one clause. Nothing is redundant against the schema, and the most decision-relevant information (the action meanings) comes first.

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 6-action, 4-param tool with no output schema, the description covers what each action does, which parameters each action requires, and the key failure case. It leaves open whether a subscribe is permanent or reversible and what the returned presence event contains, but the annotations and 100%-covered schema close most remaining gaps.

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%, and the schema explicitly defers action semantics to the description ('See the list of actions in the tool description'). The description therefore carries real added meaning for the enum values and cross-references which params each action needs, going beyond the baseline 3 for full-coverage schemas.

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?

Opens with a concrete verb+resource framing ('Presence as contacts see it') and then enumerates every action, so an agent knows exactly what the tool covers: outbound presence (online/offline), in-chat typing/recording state, and inbound presence subscriptions. No sibling tool overlaps with presence, so the scope is unambiguous 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?

Each action is described with its effect, and the description gives real operating context: typing 'shows until `paused` or the next message,' and if typing is enabled in the account's pacing the indicator is shown automatically on sends. It does not state explicit exclusions or name a preferred alternative, but there is no competing sibling for presence, so guidance is effectively complete.

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