Recent activity snapshot

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

Annotations declare readOnlyHint, openWorldHint, and idempotentHint, but the description adds valuable behavioral detail: voice transcripts without ready transcripts are marked pending and never omitted, reply decisions are explicitly not made here, and the success output is a dict with keys chats and coverage. It also mentions that unavailable accounts are reported in coverage rather than dropped (in parameter description). This goes beyond annotations with concrete guarantees.

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 description is a single paragraph but is well-structured: it opens with the core purpose, then lists return fields, notes special cases, and concludes with success format and a documentation link. It is not overly verbose, though it could be tightened without losing content. Front-loading is effective.

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?

Given the tool's complexity (10 optional parameters) and rich schema coverage, the description covers the key behavioral aspects: what is returned, the treatment of pending transcripts, the exclusion of reply decisions, and the success format. The output schema exists, so return values are documented. The link to full documentation also supplements completeness. Nothing critical is missing for correct invocation.

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 100%, so the parameters are fully documented in the schema. The description does not add additional meaning to the parameters themselves; it focuses on output structure and behavioral notes. Baseline 3 is appropriate since the schema carries the parameter documentation.

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?

The description clearly states a specific verb and resource: 'One prepared snapshot of recent activity across chats'. It explains what it returns (unread state, messages, attachments, transcripts, last incoming/outgoing) and explicitly contrasts with the alternative of 'discovering chats and then opening each one', distinguishing it from sibling tools like find_chats and get_messages.

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 implies when to use this tool ('instead of discovering chats and then opening each one') and indicates it is a batch overview. However, it does not explicitly name sibling alternatives or specify conditions when one would prefer get_messages or find_chats. The usage guidance is present but not exhaustive.

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