get_token_allowances

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

The description details the entire process: pulling Approval events, deduplication, live re-read via Multicall3, dropping zero allowances, and sorting. It also states read-only nature, no signing/broadcast, and EVM-only restrictions. This goes well beyond the annotations (readOnlyHint, destructiveHint, idempotentHint) and adds rich behavioral context.

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 quite detailed but every sentence adds value. It is front-loaded with the core purpose and logically flows through process, usage, and scope. A slight reduction from 5 due to length; however, it remains well-organized and avoids redundancy.

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 absence of an output schema, the description fully explains the return structure (fields like spenderLabel, currentAllowanceFormatted, unlimitedCount, notes). It also covers edge cases (unlimited detection) and limitations (TRON, Solana). For a moderately complex tool with 3 parameters, this is exceptionally complete.

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%, but the description adds critical nuance: for 'wallet' it specifies the role as indexed owner, for 'token' it excludes wrappers and native coins, and for 'chain' it notes default and per-chain differences. Additionally, it describes the response fields (spender, allowance details, provenance), which are not in the input schema, greatly enhancing understanding.

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 enumerates spenders with non-zero allowance for a specific token on a single EVM chain. It uses specific verbs ('Enumerate', 'Pulls', 're-reads') and explicitly contrasts with sibling tools by mentioning Solana and TRON scope limitations.

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 explicitly says when to use it ('security audits, pre-tx checks, revoke-cleanup workflows') and when not to (native coins not supported, Solana out of scope). It also provides context on per-chain differences, guiding the agent to make one call per chain.

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