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

Beyond the annotations, the description discloses a great deal: shared RPC cache, at most 18 reads, one fixed workflow charge with no per-step billing, challenge-instead-of-execution for unpaid calls, retained results on exact replay, and no free-trial or automatic paid fallback. It also bounds scope ('no complete history or security score'). It does not explain the destructiveHint=true annotation (presumably credit spend), which is the one behavioral trait left to inference.

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 purpose is front-loaded correctly, but the body is a chain of terse fragments covering billing, auth, replay, and scope with little grouping, making it hard to scan. Several statements (block pinning, snapshot reuse, no complete history) restate what the schema or annotations already imply.

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 five-parameter, paid, multi-source workflow with no output schema, the description covers the material an agent needs: cost, accepted auth paths, read ceiling, replay/charge semantics, and explicit scope limits. What it lacks is a short statement of what the returned brief actually contains structurally, though the detail parameter description in the schema partly covers output sizing.

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 100%, so the schema already explains detail, chain_id, wallet_address, contract_address, and previous_contract_snapshot thoroughly. The description adds only marginal semantic value on top — the 'one finalized Base block' pinning and the note that a returned snapshot_id is the only valid input for previous_contract_snapshot. Baseline 3 is appropriate when the schema carries the parameter burden.

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 opening sentence names a specific verb and enumerates the exact resources combined: code/proxy observations, contract-reported token facts, and one wallet's single-block ETH/Transfer evidence on a finalized Base block. That is enough for an agent to distinguish it from token_facts, contract_watch, or wallet_watch, which each cover only one slice. It loses a point because the sentence is so densely packed with qualifiers that the core verb ('combine') is nearly buried.

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 gives some routing rules — 'this workflow accepts no observation_id' and reuse of contract_snapshot_id only as previous_contract_snapshot — plus the instruction to 'Choose evidence detail before authorization'. However, it never explicitly states when to pick this combined brief over the sibling single-purpose tools, leaving the agent to infer the choice from the resource list.

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