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

Annotations only indicate this is not read-only and not idempotent, so the description must disclose behavior itself. It explains the verifier's internal asset auto-matching, accepts block-explorer URLs and extracts the hash, rejects exchange reference IDs with a specific error name, and instructs relaying assistant_guidance. It also clarifies that wallet_id is not something to ask the user for, which is a crucial behavioral rule beyond any structured field.

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?

Although lengthy, the description is organized into clear blocks: hash format, asset detection, widget-related flow, and fallback path. Every sentence carries an operational constraint or user-facing behavior. The length is justified by the complexity of the verification workflow and the number of failure modes it preempts.

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?

The tool is complete for real use: it specifies prerequisites, widget-state handling, a fallback with get_wallet_summary, and the invalid-transaction-hash error path. Since an output schema exists, the description does not need to cover return values. Nothing needed to call the tool correctly is left unattended.

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 coverage is 100% for the three parameters, which earns the baseline 3, but the description adds substantial semantic value. It documents per-chain hash formats, the handling of URLs, the rejection cases for exchange IDs, and the harmless/reflection-only nature of asset_symbol. This materially helps an agent decide what to put into transaction_hash and whether to omit asset_symbol.

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 opens with a specific verb and object: 'Submit a transaction hash for the dust/test transfer verification method.' This clearly targets the wallet-transfer verification workflow and ties it to a deposit address provided by add_wallet. The use of 'transaction hash' and 'transfer verification' plausibly differentiates it from the sibling verify_wallet_signature, even without an explicit comparison.

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 when-to-use rules: only after the user has sent a valid transfer to a deposit address, and while or when a Verify Wallet widget is, or isn't, visible. It also prescribes a concrete fallback: call get_wallet_summary first to resolve wallet_id, and it explicitly warns against a common wrong approach. This is far more actionable than most tool descriptions.

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