Transfer History

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description goes far beyond them: it discloses the window-shrinking walk-back (48->32->16->8 on archive-403s), the request cap, 60-second caching, newest-first ordering, and the meaning of each stopping condition in the note field. No contradiction with annotations; the openWorldHint is consistent with the description's reference to a public/free RPC.

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?

Every clause earns its place: mechanism, row format, filtering semantics, caching, note semantics, and an example call. It is dense and monolithic as a single paragraph rather than scannable, which taxes the reader, but there is zero dead weight.

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?

An output schema exists to cover return value shapes, and the description fills in everything else: the adaptive walk-back mechanism, free-RPC limitations, caching, parameter filtering order, and edge-case stopping conditions. An agent can invoke it correctly, interpret results, and explain failures to the user — complete for a tool of this complexity.

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 — and it does with the concrete example (symbol="AAPL", limit=10, min_value=1.0) and the crucial detail that min_value filters in token units AFTER normalization. The meaning of symbol is only implied by context and limit's behavior (row count) is inferred rather than stated, leaving small gaps.

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 clause, 'Recent ERC-20 Transfer events for a token's contract', gives a specific verb and resource that immediately separates it from all 12 siblings (quote, price_history, holder_snapshot, etc.), none of which cover transfer events. It further specifies row contents and ordering, leaving no doubt about what the tool returns.

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 clear operational context: a ~800-block adaptive walk-back, the free RPC's floating ~45-60-block window, the ~14 getLogs cap, and what the note field signals when history is unavailable ('window-closed' routes the agent to the explorer for older history). It stops short of naming a specific sibling as the alternative, but the tool's unique scope makes that omission low-cost.

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