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

With no annotations provided, the description carries the full transparency burden and does so well. It discloses per-vector confidence and its interpretation, warns that a fee recipient is indirect and never rated high, states that `estimated_volume_usd` is only an approximation and must not be quoted as settlement, and reveals that `deep=true` costs extra upstream credits. These are non-obvious behavioral details beyond the schema.

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 front-loaded with the core purpose, then follows with dense but decision-relevant caveats about confidence, pricing, fee formatting, and `deep` cost. Every sentence earns its place; there is no filler or repetition.

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 tool with no annotations, no output schema, and 0% schema parameter descriptions, this is a strong level of context. It explains the key result dimensions, evidence reliability, the approximate nature of estimated volume, exactness of fee integers, and the `deep` trade-off. It is not fully complete because it omits supported `chain` values and does not position this tool against the sibling attribution tools, but it covers everything essential for typical invocation.

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 description coverage is 0%, so the description must compensate. It adds real meaning to `deep` (credit cost and when to use), `price` (enables `estimated_volume_usd`), and transaction identification. However, the `chain` parameter is not explained at all, including what values are supported, even though the schema only provides a default of `ethereum`.

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 specifies the verb ('Classify'), the resource ('a single transaction'), and the detailed outputs: originating frontend or router, evidence, pools touched, fee recipients, and sandwich status. It is easy to tell what the tool does, but it does not explicitly contrast itself with the similarly named sibling tools `attribution` and `contract_attribution`, so it stops short of full differentiation.

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 useful conditional guidance for the `deep` parameter ('leave it off unless a shallow classification came back unattributed') and qualifies when `price=true` matters. However, it never explicitly says when to choose this tool over the sibling attribution tools, leaving when-not-to-use and alternative selection mostly implicit.

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