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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, but the description adds critical behavioral context: it fetches from trustbench.io in lookup mode, avoids database trust in offline mode, returns a specific JSON shape (receipt_id, signature_valid, on_chain_verified, etc.), and enforces that exactly one of receipt_id or receipt_json must be provided. This goes well beyond the annotations and gives the agent a clear model of what will happen.

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 description is information-dense but well-organized: one core purpose sentence, two mode explanations, a combined constraint and output summary, and an alternative-tool recommendation. It avoids redundancy with the schema and remains compact. It could be slightly more scannable with bullets, but it earns its length.

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?

Given that there is no output schema, the description thoroughly documents the return fields. It also covers both operational modes, input constraints, cryptographic algorithm, and public key source. It even mentions legacy Phase 3 SignedReceipt support. For a moderately complex tool with nested objects and multiple modes, this description leaves no significant gaps.

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% with descriptions for both receipt_id and receipt_json, so the baseline is 3. The description elevates this by explaining the distinction between lookup and offline modes, the envelope structure '{receipt, signature}', and the trust model ('without trusting the database'). It confirms the oneOf constraint and adds operational context that helps the agent choose the correct parameter for the situation.

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 resource: 'Verify the Ed25519 signature on a TrustBench receipt.' It clearly distinguishes the tool's purpose from siblings like get_receipt (which fetches a receipt) and get_rankings (which likely retrieves rankings). The two modes are explicitly named, making the scope unmistakable.

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 explicit usage guidance by breaking out two modes with concrete triggers: 'Lookup mode — pass receipt_id... handy when you only have an ID' and 'Offline mode — pass receipt_json... without trusting the database.' It also suggests an alternative for non-server-mediated verification: 'use the @trustbench/verify-receipt npm package.' This directly tells the agent when to use this tool versus when to use something else.

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