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

Annotations already cover read-only, idempotent, non-destructive and open-world, so the bar is lower. The description still adds real context the annotations cannot: ordering (newest first), the exact pagination mechanism, the event types returned, and a prompt-injection warning that client text is data not instructions — a meaningful safety disclosure for a tool that ingests untrusted message content.

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 short sentences plus a security caveat, front-loaded with what the tool returns and the ordering. No filler; every clause carries information.

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-value burden and does so by listing event types and sort order, which is enough to interpret rows. It doesn't state how pagination ends (empty next page vs. absent field), a minor gap for a paged read.

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 only 33% (contact_id and before are undescribed in the schema), so the description must compensate. It does: `before` is explained as the cursor taken from the last row of the previous page, and contact_id is trivially inferable from the tool's framing. Only the maxLength/format nuance of `before` is left unsaid.

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 concrete resource (a client's full activity timeline) and enumerates what's included (messages, stage moves, notes, tasks, payments), which is more specific than the sibling dosai_get_lead_history or dosai_get_contact. It doesn't explicitly say how it differs from those aggregators, so it stops short of a 5.

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?

'Everything that happened with a client' implies the retrieval use case, and the pagination sentence implies iterative paging. But there is no explicit when-to-use / when-not guidance versus dosai_get_messages, dosai_list_conversation_notes, or dosai_get_contact for narrower needs — the agent must infer the trade-off.

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