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

The description adds substantial behavioral context beyond the readOnly/openWorld/idempotent/non-destructive annotations: it explains that modules can move funds via execTransactionFromModule without owner signatures, describes the verdict categories, and discloses pricing, the x402 transport on Base, the prepaid header option, and the fact that no wallet or API key is required. This is exactly the kind of context annotations do not provide.

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 longer than strictly necessary and repeats the required-input information twice ('address= required' and 'Required input: address'), but it is well-structured: the core question is front-loaded, the critical module risk is emphasized, and the operational details are grouped clearly at the end. The redundancies are minor.

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 one-parameter tool with an output schema and strong annotations, the description is complete: it states the required input, the output verdict categories, the security-critical module behavior, pricing, and authentication requirements. An agent can correctly invoke this tool and interpret its purpose without needing additional context.

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 100% and the schema already documents 'address' as 'Address to check.' The description reiterates that 'address' is required and says 'Given an address,' but it does not add deeper semantics such as address format, supported networks, or validation constraints. Baseline 3 is appropriate because the schema carries the parameter documentation.

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 identifies the tool's purpose: given an address, determine whether it is a Gnosis Safe, and return owners, threshold, version, activity, and enabled modules, with a multisig / single_signer / has_modules verdict. This goes well beyond the name 'safe_check' and distinguishes the specific security-focused behavior from generic address checks.

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 gives clear context for when to use the tool: it is 'the counterparty check before you trust funds to a multisig.' It does not explicitly name alternative tools or state when not to use it, but the use case is strong enough for an agent to route appropriately.

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