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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description goes well beyond them: it discloses result ordering (newest first), the cursor pagination contract, and which fields appear in each mode. Most notably it adds a trust-boundary warning that returned text is visitor- or source-authored and must be treated as data, never instructions — behavior that appears in no annotation or schema field.

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?

Three sentences, each doing distinct work: mode split, filter/page detail, then the safety caveat. The most important information (the conversationId branch point) leads, and the safety note is placed last where it belongs as a closing constraint. No redundant restatement of the tool title or name.

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 12-parameter, zero-required read tool with no output schema, the description supplies what the structured data does not: the return shape for both modes, ordering, pagination mechanics, and an explicit instruction on how to handle untrusted content. Defaults and enum meanings live in the schema, so nothing an agent needs in order to invoke this correctly is missing here.

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 92%, so the schema already carries the parameter semantics and the baseline would be 3. The description adds real value on top by grouping parameters into the two operational modes (list-filter params vs. conversationId with its message paging) and by explaining that cursor is the nextCursor from the previous page, which orients the agent prior to reading the schema.

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 ('Read a chatbot's conversation history') and splits it into two concrete modes: listing recent conversations when conversationId is absent, and returning a single conversation's messages when present. It also names the fields each mode returns (channel, visitor type, rating, preview; messages with feedback and cited sources), so an agent can distinguish it from siblings like search_knowledge_base or view_passages without opening the 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?

The mode-selection rule is explicit and front-loaded: 'Without conversationId, lists recent conversations... With conversationId, returns that conversation's messages,' and it names the available filters (date, status, title search) and paging method (cursor). What's missing is any explicit exclusion or named alternative — nothing says when to prefer a sibling tool instead — so it stops short of a 5.

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