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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds substantive behavior: matched results include percentages and grams, an IFRA Category 4 verdict with highest safe concentration and allergens to declare, a deep link, and ranked alternatives. It also discloses sourcing ('the ratios are the library's own; nothing is invented'), the no-match fallback (returns the list of available accords), and that nothing is saved.

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 usage trigger, then output, then fallback, then sibling routing — a sensible order. It is long and reads as one dense sentence-chain, but nearly every clause carries distinct, non-redundant information about behavior or exclusions.

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?

There is no output schema, so the description carries the return-value burden and does so fully: match, percentages, grams, IFRA verdict, highest safe concentration, allergens, link, alternatives, plus the no-match path. Combined with the annotations, an agent has everything needed to call it correctly.

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 baseline is 3, but the description adds operational meaning the schema lacks: haveMaterials changes ranking (accords makeable with them rank first, missing ones listed) and concentrationPct drives the IFRA check. It also frames idea as the user's own words and batchGrams as the basis for amounts.

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 (find/matches), resource (starting formula from PerfuMate's reference accords library) and output (closest match with percentages, grams, IFRA check, link, alternatives). It is clearly distinguishable from siblings like create_formula, check_formula, and find_substitutes without opening their schemas.

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?

Explicit trigger ('when the user wants to build, create, compose or formulate a perfume... or asks what they could make with materials they list'), explicit alternative ('Re-check any edited version with check_formula'), and explicit exclusion ('Not for copying a named commercial perfume'). When-to-use, when-to-route-elsewhere, and when-not-to-use are all present.

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