Locked-token wallets on-chain

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

Annotations only declare readOnly/openWorld; the description adds genuinely non-obvious behavior: a 30-day look-back cap, coverage of 'a few dozen tokens, not the whole calendar', the covered_tokens field for discovery, and the disclosure that wallet roles marked 'our attribution' are analysis rather than project statements. Example findings show the output shape.

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?

It is a long description, but front-loaded with the core purpose and then the usage triggers, exclusions, and caveats in a sensible order. A few clauses (the parenthetical example findings, the repeated 'locked wallets' phrasing) could be trimmed without losing meaning.

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, yet the description covers what comes back (per-token roles, outflows, mints/burns, next unlock per documents, a short finding, covered_tokens), plus limits on data source and time window. An agent can call this correctly and interpret the result.

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 still adds the preference ordering (ticker preferred over name or slug) and restates the empty-token behavior in context. It does not mention the days or lang parameters, which the schema already covers adequately.

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 precise verb+resource: on-chain state of a token's locked allocations, enumerating what that includes (vesting contracts, wallet roles, outflows, mints, burns, upgrades, next unlock) and the derived finding. It is unmistakable against siblings such as get_token_unlocks or get_dataset_info.

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?

Explicit trigger phrases are given ('are team tokens moving', 'did the unlock really happen', 'who is selling'), plus the no-token fallback ('recent movements across all covered tokens') and a direct redirect: 'For the unlock calendar use get_token_unlocks.'

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