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

Goes well past the annotations: discloses rate limits (120 replies/account/hour), dedupe windows (once per comment within 7 days, per person per 30 days, 24-hour DM window), that public replies are picked at random, that link_url becomes a tracked short link, and that this messages real people without human review — consistent with destructiveHint=true. That safety framing is exactly the context an agent needs before a write with real-world side effects.

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 core action and effect, then trigger-specific rules, then the safety caveat — every sentence carries information. It is dense to the point of being a single wall of text, which slightly hurts scanability, but nothing is 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 12-parameter mutation with no output schema and openWorldHint=true, the description covers timing, scoping, rate limits, failure/sandbox constraints, and the human-approval requirement. An agent has everything needed to decide whether and how to call it.

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 92%, so the schema already carries most parameter meaning; the description still adds value by explaining cross-parameter semantics the schema does not — which params apply to COMMENT vs MESSAGE, that public_replies is randomly selected, and that link_url is appended as a tracked short link. It does not explain enabled's default/effect beyond the safety note, leaving a small gap.

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 ('Adds a rule that answers comments or direct messages automatically') and immediately delimits scope ('from now on, never older comments'). It is clearly distinguishable from siblings like update_auto_reply and list_auto_replies without opening a schema.

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 when-to-use conditions per trigger type, plus a when-not condition ('Not available in an unclaimed sandbox') and a safety protocol for the risky path ('get their OK before creating it enabled, or create it with enabled=false'). The routing between COMMENT and MESSAGE usage is fully spelled out.

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