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

Annotations already mark readOnlyHint=true and destructiveHint=false; the description goes beyond by revealing the no-key/cost-free operation, ~300ms latency, the 10-second polling restriction, and the guarantee that replies are matched exactly to the caller's thread. No statement contradicts the annotations.

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?

The description is front-loaded with a one-sentence capability summary, then uses labeled sections (examples, when to use/not, cost, latency) so an agent can scan quickly. Every section carries operational information; there is no filler.

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?

Despite having no output schema, it tells the agent what it will get back (state, messages, reply count) and how to use identifiers via examples. It also covers auth/cost and polling behavior, leaving no essential decision unresolved.

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?

All three parameters are already documented in the schema (100% coverage), so the baseline is 3. The description adds value by marking conversation_id as preferred, showing two concrete valid call shapes, and reinforcing that reference is scoped by business_number.

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?

Description opens with a specific verb and resource — 'Read a two-way conversation thread you started' — and lists concrete return contents (state, every message, reply count). This clearly differentiates it from broadly named siblings like get_status and get_outcome.

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?

WHEN TO USE gives an explicit trigger: poll after send_message with on_behalf_of returns a conversation_id. It also gives a rate-limit constraint under WHEN NOT TO USE, but it does not name alternative tools for cases that don't match, so it is a 4 rather than a 5.

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