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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds value by disclosing that it works offline (no network calls), that it uses the same trusted key as other tools, and that it detects both altered receipts and receipts never signed by SaSame. This goes beyond the annotation's safety hint and clarifies the operational behavior, though it doesn't specify the return format or error handling.

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 two sentences with no redundancy. It front-loads the core purpose, then gives input sourcing instructions. The inclusion of issue numbers (#1475/#1768) is minor noise but not harmful. It's concise and well-structured, though not minimal.

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?

With no output schema, the description fails to explain what the tool returns. The agent doesn't know if the result is a boolean, a structured verification object, or an error. While it states the detection capability, it doesn't specify the output format or any error conditions (e.g., malformed signature). This is a significant gap for a verification tool that the agent needs to interpret.

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?

The schema already provides full coverage of the receipt object (all required fields, types, and a description). The description adds meaningful context by telling the agent where to obtain the receipt (from station_receipts or receipt_history via factory_status/factory_start), which is not in the schema. This compensates for the high schema coverage baseline and helps the agent source the correct input.

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 clearly states the tool's function: it offline-verifies a Factory receipt's ed25519 signature against SaSame's trusted issuer key. It specifies the exact signature fields (signed_by/signature), the cryptographic method (ed25519), and what it detects (tampering or non-original receipts). This is a specific verb+resource pair that distinguishes it from siblings like trust_pubkey (returns the key) and verify_mcp_cert (verifies certificates), even though it doesn't name them directly.

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 input usage guidance ('Pass any receipt object exactly as returned by factory_status/factory_start/etc') but does not explicitly say when to choose this tool over alternatives. It references trust_pubkey and verify_mcp_cert as using the same key, which implies a relationship, but there's no clear 'use this when' or 'use that when' statement. The context is helpful but not fully prescriptive.

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