token_transparency

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

With no annotations, the description carries the full burden and does disclose meaningful behavioral traits: data is read live from Base, the feeRecipient is read from the contract, verdicts carry an 'n' sample size, balance checks are against a named block with a two-sided MISMATCH flag, and contracts are explicitly UNAUDITED. These are exactly the caveats an agent needs before presenting results as authoritative. It does not state read-only semantics explicitly, nor failure modes for an unknown symbol, keeping it below 5.

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 entire description is one sprawling run-on sentence that dumps roughly a dozen output categories without grouping, hierarchy, or front-loading of the most important facts. The UNAUDITED caveat, arguably the most critical detail, is buried at the very end. It is informative but structurally poor and hard 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?

There is no output schema, so the description must explain the return surface, and it does so thoroughly: fee routing, ownership, upgrade timelock, verification links, unlock timing, graduation liquidity, volume, net flows, balance/mismatch checks, fee reconciliation, creator_traded states, and milestone logs. The main gaps are error/unknown-token behavior and any notion of output shape (flat vs nested).

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 single 'token' parameter is fully documented in the schema as 'symbol (APBUILD, APAD) or 0x token address', so coverage is 100%. The description adds no further semantics about the parameter, such as case sensitivity or behavior on ambiguous symbols. Baseline 3 is appropriate when the schema does the work.

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 framing, 'Where the money goes for an AgentPad token, read live from Base', and enumerates the exact artifacts it returns (fee wallets, feeRecipient, owner, timelock, Sourcify links, unlock schedule, graduation liquidity). This clearly separates it from siblings like get_token, honest_volume, and agentpad_info, which cover narrower slices. It stops short of a single crisp verb+object statement such as 'Returns a token transparency report', so it is strong but not maximally sharp.

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?

There is no explicit instruction on when to call this versus get_token, honest_volume, or agentpad_info, even though those siblings overlap on fields like volume and token metadata. The context ('due diligence on a token') is implied by the enumeration but never stated. An agent must infer routing from field lists alone.

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