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

Annotations declare readOnlyHint=false and destructiveHint=false, which alone don't tell the agent why this is a write; the description supplies that the thread read 'mark[s] it read', a real state change. No contradiction, and the side effect disclosure is genuine added value, though auth/rate-limit context is left to the schema.

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 compact clauses, front-loaded with the default (no-parameter) behavior first. Every word earns its place with 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?

For a two-mode tool with full schema coverage and no output schema, the description covers both branches adequately. It stops short of noting what the listing/thread returns beyond unread counts, a minor gap.

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 100%, so the baseline is 3, but the description adds meaning beyond 'Handle of the other profile (optional)': the presence of `with` switches the tool's entire operation rather than just filtering results.

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+resource and splits behavior by mode: listing conversations with unread counts vs reading a full thread. This clearly distinguishes it from siblings like read_feed, get_post, and send_message.

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 explicit conditional routing: omit `with` to list conversations, supply `with` to read a thread. It does not name alternative tools or exclusion conditions, so it falls short of a full when/when-not statement.

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