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

Adds a lot beyond annotations: spends credits, sends nothing, async jobId return, 1-4 minute latency with the slow case identified, and that it follows workspace standing negotiation rules autonomously. These are the exact behavioral traits an agent needs and none are in the 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?

Front-loaded with the two most decision-relevant facts ('SPENDS CREDITS. Sends nothing.'), then rationale and mechanics. Dense and mostly efficient, though a few sentences run long.

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 mutation tool with no output schema, the description covers cost, side effects, return value (jobId), polling path, latency and autonomous rule-following. Nothing needed to call it correctly 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 coverage is 100%, so the schema already documents mode, pageUrl, guidance, skipPageUrls and avoidAfterTexts. The description only restates the guidance parameter's purpose; it adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 and returns a jobId') and names the polling sibling. An agent can distinguish this from edit_draft or send_reply purely from the text.

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 it 'rather than writing the reply yourself when the answer should propose a placement', explains why (site crawling it can't do from thread text), and routes the follow-up to get_draft_reply. It also warns not to write a replacement while it runs.

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