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

Annotations already establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by disclosing the cost per call and the dual-mode behavior (judge vs deep scan), which are not in the annotations. It also clarifies the scope (user-generated content and yield-vault listings). No contradictions with annotations.

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 two sentences, with the core purpose in the first and essential cost/replacement guidance in the second. There is no fluff or redundant restating of the title. It is front-loaded with the action and resource, making it easy for an agent to quickly understand the tool's function.

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 tool has only 2 parameters, both fully described in the schema, and no output schema to explain. Annotations cover side effects. The description fills the remaining gaps by explaining the tool's purpose, cost, and pointing to alternatives. It is complete enough for an agent to select and invoke it correctly, though it could briefly mention return format for each kind, but the schema already hints at that.

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% — both 'kind' and 'content' are already fully described in the schema (e.g., enum values for 'judge', 'deep_scan', 'vaults' are explained). The tool description does not add significant new semantics beyond what the schema provides. Per the baseline, with high schema coverage, a score of 3 is appropriate.

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's function: 'AI moderation and integrity scanning for user-generated content and yield-vault listings — judges content quality and runs a deep integrity scan for manipulation.' It uses a specific verb ('judges', 'runs'), names the resource ('user-generated content', 'yield-vault listings'), and distinguishes from sibling tools by focusing on content integrity rather than market analysis or token safety.

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?

The description provides practical usage guidance by noting that it's a paid service ($0.05–$1.00 per call) and that 'free alternatives exist for several of these — see list_einstein_capabilities.' This tells the agent when the tool might be worth using (for advanced integrity checks) and directs to an external list for cheaper alternatives. However, it does not explicitly name a 'use instead' sibling tool, so it's slightly less direct than a top-tier example.

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