set_conversation_preferences

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

With annotations only covering readOnly/idempotent/destructive, the description adds substantive behavior beyond them: partial-update semantics ('only the settings you pass change'), one-request-per-setting, and non-atomic failure reporting where earlier settings persist and the error names the failing one. It also flags the 'default' notification-level restriction, which is real behavioral guidance not derivable from structured fields.

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 behavioral summary is front-loaded and tight, and the per-argument list is justified given zero schema descriptions. It is slightly longer than strictly necessary (the Returns line duplicates the output schema), but no sentence is 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?

For a 7-parameter mutation tool with no schema descriptions and only terse annotations, the definition covers scope, partial-update behavior, failure semantics, and every parameter's meaning. The output schema exists, so the description need not explain return values, and its brief mention is harmless rather than a gap.

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 description coverage is 0%, so the description carries the full burden, and it does: every one of the seven parameters is explained in plain language, including the accepted enum values for notification_level ('always'/'mention'/'never') and the archive/notification side effects of archived, important, sensitive, and call_notifications. This is a strong compensation for the empty schema.

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 (change) and resource (your own per-conversation settings) and immediately scopes it with 'other participants are not affected', which separates it from sibling mutations like update_conversation, set_participant_role, or set_thread_notification_level. An agent can identify the correct tool without opening any 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?

The description makes clear this is a personal-preferences update rather than a conversation-wide change, and the per-parameter notes imply when each setting applies (e.g. notification_level 'default' is not accepted, so the agent must choose a value). It stops short of explicitly naming alternatives or stating when-not-to-use.

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