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

The description uses 'Read' to indicate read-only behavior and details what is returned, including the null return case. However, since no annotations are provided, it does not cover aspects like cost, authorization, or side effects. Still, the read intent is clear and sufficient for most agents.

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 a single sentence that efficiently conveys the tool's purpose and return data. It is front-loaded with key information and contains no extraneous words.

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?

Given the complexity of a multisig state read with multiple components, the description covers all essential return fields (members, permissions, threshold, vault balance, pending proposals with vote details) and the null behavior. No output schema exists, so the description compensates fully.

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 input schema fully describes the single parameter 'address' with regex and description. The tool description does not add additional meaning beyond what the schema provides. Per the rule for high schema coverage, 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 the tool reads a Squads v4 multisig by address and enumerates the specific data returned: members, permissions, threshold, vault balance, and pending proposals with vote tallies. It also mentions the null return for non-multisig addresses. This distinguishes it from sibling tools that create, approve, or execute proposals.

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 implies usage for reading multisig state, but does not explicitly contrast with alternative tools like multisig_create_build or multisig_approve_execute. It provides context by listing what is returned, but lacks explicit 'when not to use' or alternative recommendations.

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