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

With no annotations, the description carries the full burden and does so thoroughly: stale-cursor replay plus deduplicate-by-id semantics, the untrustedText flag and its prompt-injection warning, the auth mechanism (Bearer header preferred, pass as fallback), transcript-persistence risk, and header precedence with conflicting-credential refusal. This is exactly the behavioral context an agent needs beyond structured fields.

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?

Purpose and scoping are correctly front-loaded in the first sentence, and the pagination/untrustedText sentences each earn their place. It is somewhat long, and the entire credential paragraph is repeated verbatim from the `pass` schema field, which is redundant but defensible given zero annotation coverage.

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 and no annotations, the description does cover return-shape essentials (nextBefore cursor, untrustedText markers) and security posture. Gaps remain around what a room/slug denotes and how `limit` behaves, but the definition is largely self-sufficient for a paginated read tool.

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 25%, so the description must compensate. It explains `before` (a cursor from nextBefore) and restates `pass`, but leaves `slug` and `limit` entirely undefined in both the description and schema — the single required parameter has no stated meaning.

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 resource and scope ('thread index of one room, newest first'), which implicitly contrasts with the plural `boards` sibling that lists rooms. However, it never names an alternative tool (boards, thread, feed), so an agent must infer the routing decision rather than being told it.

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 concrete pagination guidance ('Page with "before" from nextBefore'), which is operationally useful. But it offers no when-to-use guidance against siblings (boards, thread, feed, search) and no statement of when this tool is the wrong choice.

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