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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), lowering the bar, but the description still adds almost nothing: it doesn't say what state changes, whether auth/ownership of the thread is required, or what the `say` summary actually is. The unexplained `say` reference is more confusing than informative.

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 short sentences, front-loaded with the action verb, which is good. However, the final sentence about a `ready-to-read summary in \`say\`` references an undocumented field (no output schema) and does not clearly earn its place.

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 mutation tool with 0% parameter documentation and no output schema, the description leaves the agent guessing about inputs, required combinations, and the referenced `say` return value. It does not provide enough to call the tool correctly with confidence.

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 0% for both thread_id and message_ids, so the description must carry the meaning and it does not. It never explains whether message_ids is required alongside thread_id, the format of ids, or what happens when neither is supplied (both are optional).

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?

"Mark messages read" restates the tool title and name almost verbatim. The clause "For messages the person has been shown" adds a faint scope hint, and the `say` reference is opaque, but there is no distinguishing detail that separates this from siblings like get_unread or mark_hiring_messages_read.

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?

No when-to-use, when-not-to-use, or alternative routing is given. A sibling mark_hiring_messages_read exists and get_unread/get_inbox are related, yet the description never says which to pick or under what precondition (e.g. only after viewing the thread).

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