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

Annotations already declare readOnlyHint and idempotentHint. The description adds meaningful context by disclosing false-discovery control and that coverage confounds are flagged as measurement artifacts, never findings. This goes beyond simple read-only behavior and clarifies interpretive nuance.

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?

Three sentences, front-loaded with the core purpose. Each sentence earns its place: purpose, usage alternative, and scope caveat. No fluff, and the technical terms (e.g., false-discovery control) are dense but precise.

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?

The description is complete for a parameterless, read-only board verdict tool. It explains what the tool does, when to use it, how to follow up (get_signal), and explicitly separates censorship board from AI-model-evaluation scope. No output schema is present, but no return details are necessary for this conceptual tool.

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?

The tool takes zero parameters, and the schema fully covers that with an empty object. The description redundantly states 'Takes no arguments,' which adds no new meaning but is harmless. Baseline 4 is appropriate for parameterless tools.

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 clearly states the tool judges whether anything is happening in Chinese censorship across all signals, with a specific verb ('Judge') and resource ('cross-signal verdict'). It explicitly distinguishes from siblings by advising to use this instead of fetching individual signals and then using get_signal to drill down.

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?

Provides explicit when-to-use guidance: 'Use this instead of fetching signals individually and reconciling them yourself; then use get_signal to drill into whichever signal moved.' Also includes a scope note excluding the AI-model-evaluation side and directing to get_signal with specific parameters, giving clear alternatives.

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