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

With no annotations, the description carries the full burden. It details return fields (reviewer domain, date, offering, verdict, validity, evidence tier) and explains the evidence-verified tier's additional signature and attestation. It implies a read-only operation and independence from trust, but does not cover error cases or rate limits.

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 structured with a clear first sentence, then usage guidance, then return details, then a free note, then the use case. It is slightly verbose with the trust chain example but overall justified. No redundant sentences.

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 the existence of an output schema, the description does not need to detail return values. It covers purpose, usage context, behavioral traits, and parameter guidance sufficiently. All key aspects are addressed for a verification tool.

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 the parameters are already well-documented. The description does not add new meaning beyond what the schema provides (e.g., keccak256 hash, 0x-prefixed hex). Thus, the description adds minimal value beyond the schema for parameter semantics.

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 action ('verify') and the resource ('a Taste content certificate on-chain'), providing a specific verb and resource. It distinguishes itself from siblings like verify_external_source and verify_reasoning_chain by focusing on Taste certificates and evidence tiers.

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 explicitly states when to use: 'Call when consuming content from another source that claims to be human-reviewed'. It also notes it is free, which aids usage decisions. However, it does not explicitly mention when not to use or provide direct alternatives, though the context of sibling tools is available.

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