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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), and the description adds a great deal beyond them: it spends credits, sends nothing, is asynchronous with a 1-4 minute runtime, follows the workspace's standing negotiation rules, and writes a placement record that other tools consume.

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?

Front-loaded with the two highest-value facts (spends credits, sends nothing) and tightly packed, though the aside about the placement record and the negotiation rules adds length that is useful but not essential.

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 an async, credit-spending, open-world tool with no output schema, the description covers cost, side effects, async contract, polling target, timing, and rule inheritance. Nothing an agent needs before invoking it is missing.

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 100%, so mode, pageUrl, guidance, skipPageUrls, avoidAfterTexts, and conversationId are already fully documented in the schema. The description only adds light usage framing ('Pass guidance to steer what it offers'), which is the baseline-3 case when the schema does the heavy lifting.

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 and resource ('starts MentionAgent's own reply writer on one thread'), the immediate return ('returns a jobId'), and the follow-up tool to poll. It is clearly distinguishable from siblings like edit_draft, send_reply, and answer_link.

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?

Explicitly says to use this rather than writing the reply yourself when a placement should be proposed, and warns 'do not write your own replacement while it runs'. It also cites the reason (site crawling and paragraph selection) that rules out the manual alternative.

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