Recent activity

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine behavior beyond that: results are ordered most recent first, aggregation is per chat, and there is an explicit 'waiting for the user's reply' flag. It does not disclose pagination, caps on the number of chats returned, or cost/latency considerations, which keeps it below 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?

Two compact blocks: the purpose/return summary first, then per-parameter notes, each sentence load-bearing. Front-loaded correctly with the highest-value information. Minor deduction for the slightly fragmented line-wrapped phrasing that reads like an unstyled bullet list.

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 an output schema present, return values needn't be spelled out, yet the description still characterizes the payload (counts, latest few, reply flag) helpfully, and annotations cover the safety profile. Defaults (since=24h, per_chat=5) and the exact 'chats' identifier format are the remaining holes an agent might need before calling.

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 0%, so the description carries the full burden and largely meets it: 'since' gets concrete format examples ('24h', '7d', '2026-09-01'), 'per_chat' gets a meaning plus an undocumented cap of 20, 'kind' is glossed per enum value, and 'chats' is described as a limiting filter. The gap is 'chats', where the accepted identifier form (string usernames vs integer ids) is never clarified for a union-typed array.

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 and result shape: 'What happened recently across chats, most recent first: per chat the number of new messages, the latest few, and a flag on chats waiting for the user's reply.' An agent immediately knows this is an aggregated digest, not a raw message dump. It doesn't explicitly contrast itself with siblings like list_chats, get_messages or search_messages, so it misses the top mark.

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 'Use for "what's new", "what did I miss" and "who am I owing an answer"' line gives strong user-intent triggers that map directly onto selection decisions. However, it never states when NOT to use it (e.g., for a full message search use search_messages, for a single chat's history use get_messages), so no exclusions or named alternatives are provided.

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