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

Annotations only establish read-only/non-destructive, but the description adds cost and auth context ('Free; no API key, wallet or payment'), default vs. non-default checking behavior, and explicit scope limits ('VERIFIED is not finality, ownership, causality, asset-balance change verification or a swap economic-outcome guarantee'). It also warns that 'missing evidence is not success' and that readouts should come from http_status, response.verification.state and response.observation_errors, which goes well beyond the annotations.

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 usage trigger is front-loaded in the first clause and nearly every sentence carries load-bearing information (cost, defaults, scope exclusions, sibling routing). It is dense to the point of being clause-heavy, but there is little that could be cut without losing an actionable constraint.

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 verification tool with a nested expectation object, a sibling tool and an existing output schema, the description covers the calling context, defaults, cost, scope and error interpretation well; return-value explanation is rightly delegated to the output schema. The remaining gap is the precise comparison semantics of the candidate fields, which an agent must infer.

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 does partially: transaction_hash is named as required, the expectation categories (inclusion, receipt_status, candidate) are named, and the inclusion default is alluded to. However, it does not explain candidate-field matching semantics, the chain_id constraint, or the candidate field shapes, leaving real gaps against a zero-coverage nested schema.

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 states a specific verb (verify) and a precisely scoped resource (a Base Mainnet 8453 transaction), and enumerates what is checked: explicit inclusion, receipt-status, optional candidate-field expectations. It also names the sibling preflight_transaction, so an agent can separate this from its counterpart without reading any schema.

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 an explicit when-to-use ('After independent broadcast') and an explicit alternative with its own condition ('Before signing use preflight_transaction'), plus the default-behavior caveat ('default checks inclusion, NOT receipt success'). An agent knows both when to call this and when to call the sibling instead.

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