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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), yet the description still adds genuinely new behavior: a hard scan limit of the 50 most recent active chats, newest-first ordering, and the meaning of an empty result. It doesn't say what happens when the 50-chat cap is hit and matches are truncated, which is the one operational caveat left unstated.

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 purpose and window are front-loaded, then the scan behavior, then the return fields, then the alternative — a sensible ordering. The long parenthetical enumerating every return field is dense and reads as a run-on, but it is load-bearing because no output schema exists.

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 no output schema, the description carries the return-shape burden and does so: chat_jid, last-message time/sender, preview, and the contact fields with their value semantics (name_source enumerations, canonical_jid usage, null conditions for phone_jid/lid_jid). An agent has enough to call the tool and interpret results.

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?

With 100% schema description coverage and a single optional parameter, the schema already carries the default and max, and the description's restatement of "default 24, max 72" is largely duplicative. Baseline 3 applies; no additional semantics such as how the window interacts with the 50-chat cap are given.

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 and resource (lists one-to-one chats) plus the defining filter: last message from the other person within the hours_ago window. It explicitly excludes groups and names the sibling get_recent_chats as the contrasting scope, so an agent can distinguish the two without opening either 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?

Gives an explicit triggering intent ("Use it for 'who do I need to reply to?'") and a named alternative with the condition that selects it ("For a general look at recent activity, including groups and chats where the user wrote last, use get_recent_chats instead"). Both when-to-use and when-not-to-use are covered.

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