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

Annotations already cover readOnly, idempotent, and non-destructive behavior. The description adds valuable context: it is a 'live' analysis (results may change) and explicitly discloses the cost range ($0.35–$2.00 per call) from the Einstein credit balance, which is critical for agent decision-making. It also notes that free alternatives exist, adding cost-awareness beyond 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?

Two sentences, with the core purpose front-loaded and the cost note appended. Every word earns its place, and the structure is clear and scannable. No redundancy.

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 covers the purpose, analysis types, and cost, but does not indicate what the output looks like (e.g., a risk score, report, or list of findings). Given there is no output schema and the tool is paid, the agent would benefit from knowing what to expect in the response. Overall adequate but with a clear gap in return-value description.

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%, with detailed parameters especially for `kind` and `chain`. The description only adds the direction to choose the analysis with `kind`, which is already evident from the schema. Since the schema documents parameters thoroughly, the description adds minimal extra meaning, so the baseline 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 it performs 'live security analysis of a token contract' and enumerates specific analysis kinds (rug-pull, holders, sniping, approvals, contract audit). This specific verb+resource combination, along with the distinct analysis types, distinguishes it from broader scan tools like check_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?

It instructs the agent to choose the analysis with `kind` and mentions free alternatives via list_einstein_capabilities, but it does not explicitly specify when to use this tool versus related siblings like check_token_safety or when to avoid it. The usage context is implied rather than stated.

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