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

Even though annotations already mark this as read-only and non-destructive, the description adds auth requirements ('Public, no auth for the basic audit'), rate limits ('Daily caps per caller'), and what deep returns (bounded reply_sample with bot-isms vs human reaction). It also discloses the metric methodology and honest scope limits. This exceeds the structured fields substantially.

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?

The description is dense but front-loaded: its first sentence states the core purpose and output format, then follows with supporting metrics and constraints. No sentence is wasted; every clause adds call-relevant information like engagement weights, deep-mode behavior, and access limits.

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 tool with no output schema, it explains return values precisely (score, verdict, engagement-unit weights) and the deep-mode addition. It also covers access limits, auth, and scope caveats, leaving an agent with everything needed to call it correctly.

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?

Input schema already covers both params at 100%, so baseline is 3. The description adds meaningful nuance to 'deep' — it returns a bounded reply_sample and is restricted to Builder/Pro plans — and confirms handle can include or omit @. This extra elaboration warrants a 4.

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?

The description opens with a specific verb ('audit') and resource ('any X @handle'), then details the output: 0–100 score, ORGANIC/MIXED/SMOKE verdict, and a weighted engagement metric. This clearly separates it from any other tool, including the 'audit_history' sibling, making its purpose unmistakable.

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?

It explicitly scopes when to use it ('give it any X @handle') and notes the optional deep variant for paid plans, daily caps, and public no-auth access. It doesn't name alternative tools to rule out, but since no sibling performs account audits, the context is sufficiently clear. This earns a 4 for clear context without explicit when-not guidance.

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