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

Annotations already mark readOnly, idempotent, and non-destructive. The description adds meaningful operational facts: local decoding, no wallet connection, no contract-safety evaluation, no application persistence, and remote processing. These constraints materially affect invocation expectations and go well beyond annotation coverage.

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 compact and front-loaded with the core purpose, followed by exclusions and input-retrieval instructions. Every sentence earns its place; there is no filler or redundant restatement of the tool name.

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 7-parameter tool with an output schema, the description covers purpose, exclusions, input retrieval, and persistence behavior. The only notable gap is that ERC-1155 appears in the enum but the description only illustrates the ERC-20 vs ERC-721 distinction.

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 schema covers all seven parameters with descriptions and an enum, so the description does not need to repeat per-parameter details. The text adds conceptual orientation around recipient/spender and atomic amount but no concrete parameter-level guidance beyond the schema. 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?

States a specific verb ('decodes') and object ('supported token-call shapes'), and frames the comparison against recipient, spender, and atomic amount. The negative capability list separates it from safety and simulation tools. Clear and differentiating.

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?

Names fetch and read as the way to retrieve calls and exact inputs, providing an explicit path to invocation. It also lists exclusions such as no chain simulation and no safety verdict, so an agent knows when not to use it. It does not name specific alternative tools for those excluded jobs.

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