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

Annotations already establish read-only and idempotent, and the description goes well beyond them: truncation signals, capped message bodies with no media, the timestamp each entry type anchors to (task completion/creation, alarm time, note last edit), access-scope exclusion of out-of-scope chats, and an explicit UNTRUSTED-content warning. These are exactly the operational facts an agent would otherwise discover only by misusing the tool.

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?

Front-loaded with scope, then entry shape, then filters and limits, then caveats — a sensible order with no filler. The telegraphic, colon-heavy style is dense enough that a first-time reader may need a second pass, but nothing is wasted.

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 four-parameter aggregation tool with an output schema, this covers everything an agent needs: what is merged, ordering, pagination/truncation semantics, filtering, per-kind timestamp meaning, and the safety caveat about customer-authored text. No material question is left open before the call.

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 has to carry the load, and it does: it supplies the limit default of 50 (absent from the schema, which only caps 1-200), the meaning of truncated as 'older entries exist', and the point of kinds/since as filters. It does not explain the contact_id pattern or say what since filters on (event time vs. created time), which is the one real gap.

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 — 'One contact's history as one list, newest first' — and enumerates the merged kinds (messages, stage moves, tasks, alarms, notes, identity events). An agent can immediately tell this apart from get_contact (attributes), list_messages (one chat's messages) and get_conversation 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?

Gives concrete guidance: filter with kinds and since, and route to list_messages when full message text is needed. It does not explicitly state when to prefer this over get_contact or get_follow_up_queue, but the merged-history framing makes the choice obvious in most cases.

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