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

Annotations already cover read-only/no-destroy/open-world, so the bar is low, yet the description adds substantive context: deprecation status and hard rate limits (6 calls/minute, max one call per 10s). Those operational constraints are not derivable from any structured field.

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, zero filler, and the deprecation marker is front-loaded so an agent sees it before committing. Every clause carries distinct information (purpose, return fields, motivating use case, rate limits).

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?

No output schema exists, but the description names the returned fields, which is sufficient for an agent to use the result. The one real gap is that a deprecated tool does not point to its replacement, leaving the agent without a migration path.

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 both parameters carry their own descriptions with concrete symbol/chain examples, so the description need not restate them. It does not add syntax, casing, or alias rules beyond the schema, so the 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?

States a specific verb and resource ('Get a token's on-chain metadata') and enumerates the returned fields (display name, decimals, EIP-712 version) plus the chain scoping. This is clearly separable from siblings like get_config or get_balances without opening any schema.

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?

Gives a concrete use condition: it is 'needed when building an EIP-3009 deposit signature's tokenName/tokenVersion fields.' It also flags deprecation, which is a negative-usage signal, but names no replacement tool or explicit alternative, so the routing guidance is incomplete.

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