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

With no annotations, the description carries the full burden and does so thoroughly: cost ($0.02 USDC on Base), cursor ownership semantics, required recovery token and its transport for REST vs MCP, idempotency rules, the rule that provider failure/partial scan never becomes a paid success, and what observation_saved=false plus persistence_error means (do not use returned IDs, retry recovery only). Retention windows and 429 capacity behavior are also disclosed.

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, but the body is a ~250-word run-on mixing payment plan terms, trial credentials, tariff grants, and legacy web package language, much of which does not change tool selection or invocation. Sentences like 'Historical web package terms remain unchanged' do not earn their place.

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 an 8-parameter paid read with no output schema, the definition covers the important unknowns: pagination via cursor, bounded finalized pages, gap failure, has_more semantics, error/pending states, and cost. It stops short of describing the actual snapshot payload shape, but the flags and ID caveats it does surface cover the risky parts.

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 every parameter is already documented in the schema; the baseline of 3 applies. The description adds a little beyond the schema — that the cursor must be persisted and that the next page requires a new paid operation — but contributes no field-level semantics the schema lacks.

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 gives a specific verb (Read) and precise resource (ETH balance snapshots and selected ERC-20 Transfer events for one wallet, bounded finalized page), and explicitly excludes what it is not (full native/internal/NFT/transaction history). It distinguishes scope well, though it never names a sibling tool to steer against.

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?

It gives concrete operational guidance — persist the cursor, use a new paid operation for the next page, use an approved payment client, accept /v3/prepaid/all-services terms before purchase, and there is an optional free trial path. However, it never states when an agent should pick this over fresh402_contract_watch or fresh402_token_facts, so sibling selection is left to inference.

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