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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is covered. The description adds genuinely useful non-obvious behavior: strict name matching where generic tokens like "peptides" or "labs" never match, and ambiguous names degrading to a candidate list instead of a guess. It does not cover failure modes for unknown-but-specific names beyond the "not evaluated" state, but that is a minor gap.

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?

Front-loaded with the core value proposition and then the fallback outcomes, with no filler sentences. The semicolon-chained enumeration of return shapes is dense but each clause carries distinct information. It reads as one long sentence, which slightly hurts scanability.

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 one required parameter, no output schema, and full schema coverage, the description carries the remaining burden well: it describes the return payload, the two non-standard result states, and the matching rules. Nothing an agent needs in order to call this correctly is missing.

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%, so the baseline is 3; the description earns an extra point by defining the matching semantics of the single "name" argument. The clause that generic words never match and ambiguous inputs return candidates materially changes how an agent should construct and interpret the argument, which the schema does not say.

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?

States a specific verb and resource ("independent audit of a research-peptide vendor") and enumerates exactly what comes back: PepScore grade and band, COA status, audit summary, buy link, or the COA-audit record, or "not evaluated". That is far more precise than the name alone. It stops short of naming siblings such as list_verified_vendors or find_peptide_sources, so an agent must infer that this is the single-vendor lookup.

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?

Usage is implied through the three outcome branches (graded, audited-but-not-graded, not evaluated), which tells an agent this is the authoritative single-name lookup. There is no explicit when-to-use framing against the sibling tools or any stated prerequisite, so the agent must infer that this is the right call when it already has a vendor name.

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