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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower. The description adds meaningful behavioral context beyond annotations: it discloses data scope ('totals only, no wallets') and caching ('cached about a minute'), which directly affects how an agent should interpret freshness.

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 compact sentences, front-loaded with the core action and resource, then the field enumeration and caching caveat. No wasted text.

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 single-parameter, no-output-schema read tool with annotations covering safety, the description supplies enough: what data is returned, scope limits, and caching. Minor gap is the absence of any hint about output shape, though no output schema exists.

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%, so the enum values and 'leave out for both' behavior are already documented in the schema. The description adds no parameter-level detail beyond that, so baseline 3 applies.

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?

Specific verb+resource: reads public vault totals from chain, enumerating what is returned (holdings, deposit/transfer/cashout/message counts). Distinct from siblings, which are action-oriented (create, deposit, verify). Lacks explicit sibling differentiation but purpose is unambiguous.

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?

Usage is implied by the read-only stats framing and the network parameter's 'leave out for both' guidance, but there is no explicit when-to-use or when-not-to-use guidance versus alternatives like gloam_info or gloam_networks.

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