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

Annotations only cover safety (read-only, idempotent, non-destructive); the description adds real behavioral context beyond them: each query draws the org AI token budget, results are UNTRUSTED customer content with an injection warning, and the agent must consult index_status/history_gap before reporting no results. That is exactly the kind of cost and failure-mode disclosure annotations cannot carry.

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 what it searches and when to reach for it, then layered behavior warnings. Dense but nearly every clause carries new information; the packing of four distinct directives into two sentences costs a little readability.

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?

An output schema exists, so return values need no explanation, and the description covers the remaining risk areas: cost per query, untrusted content, empty-result verification, and date-range usage. The only soft spot is that index_status and history_gap are referenced but not among the listed sibling tools.

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?

At 71% schema coverage the schema already documents from, to, labels, conversation_id and variants. The description still adds meaning: it explains why variants exist (word matching plus translations into customer languages) and ties from/to to a period named in the question. query and top_k get no semantic help in the description, keeping it below a 5.

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 ("Search past WhatsApp messages ... plus contact interaction summaries") with explicit scope: text, media captions, voice-note transcripts, keyword AND semantic matching. That scope cleanly separates it from list_messages (enumeration), search_contacts (contacts only) and kb_search (knowledge base).

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 a concrete triggering example ("who asked about pricing last month") and conditional instructions: send variants for rephrasings/translations, and from/to when the question names a period. Missing explicit exclusions — it never says when to prefer list_messages, get_chat_summary or search_contacts instead, which matters given the crowded sibling set.

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