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

Annotations already declare read-only, idempotent, and non-destructive hints, but the description adds meaningful behavioral context: the server never holds caller wallets, so no balance is returned, and symbol lookups only work on configured chains. This goes well beyond the structured annotations and clarifies limits.

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 concise and front-loaded, with the core purpose in the first sentence. Each subsequent sentence adds necessary operational detail (token format, no balance, required fields, supported chains) with no filler. The organized structure makes it easy for an agent to scan.

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 simple read-only tool with two parameters and an output schema present, the description is complete. It covers what the tool does, how to pass parameters, safety characteristics, supported chains, and requirements. The output schema handles return value details, so no further description is needed.

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%, so the baseline is 3. The description adds value by restating that both parameters are required, providing concrete examples like 'USDC' / 'USDC.e', and noting that symbol lookup is conditional on chain configuration. This extra context justifies a score above baseline.

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 opens with a specific verb and resource: 'Read ERC-20 token metadata — name, symbol, decimals, total supply — for a token contract on an EVM chain.' This clearly distinguishes the tool from siblings like network.token_price by focusing on metadata, not pricing, and explicitly notes it never returns balances.

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 provides clear context for when to use this tool: it is free, read-only, and returns only public metadata. It also explains the token parameter format (address or symbol) and caveats that symbol lookup depends on chain configuration. However, it does not explicitly name alternative tools or state 'use X instead' for cases like price queries, which keeps it just below a 5.

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