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

With no annotations, the description carries the full burden and does contribute two genuine behavioral facts: chronological ordering and a prompt-injection warning that customer-authored content must be treated as data, which is valuable beyond any structured field. It does not disclose pagination/limits, whether the call is read-only, permission requirements, or behavior on an empty or unknown conversation.

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, both front-loaded with the essential facts (what is returned and in what order; then the trust boundary). No filler or redundant restatement of the tool 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?

The return shape is covered by the output schema, so omitting it is fine, and the injection warning is a meaningful addition. However, for a tool whose only parameter is completely undocumented, the description should at least state the id's origin and any paging behavior, which it does not.

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?

The single required parameter conversation_id has 0% schema description coverage and the description never mentions it, its UUID format, or where to obtain it (presumably from phone_threads). The description neither compensates for the coverage gap nor adds any meaning beyond 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 the resource and scope specifically: the messages belonging to a single text thread, in oldest-first order. The word 'one' implicitly separates it from phone_threads, but the distinction is not made explicit and no verb (fetch/list) is used, leaving the agent to infer that this is a read operation.

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?

Usage is only implied: 'one text thread' hints that this is the single-thread counterpart to phone_threads, but neither that sibling nor any when/when-not condition is named. An agent must infer that a conversation_id from phone_threads is the intended input.

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