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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), yet the description still adds real context: it does not save or alter amounts, it returns a PerfuMate link, it evaluates IFRA Category 4 at a user-chosen concentration, and unmatched lines are listed but not counted. Missing only finer details such as exact return structure, which is largely fine given the read-only profile.

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?

A single dense paragraph, but it is front-loaded with the trigger and each sentence carries distinct information (trigger, verdicts, category, input format, edge cases, exclusions, return link, alternatives). Slightly long but no filler.

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?

Covers the trigger, both input formats, the unit rule, unmatched-material behavior, the mutation disclaimer, and the returned link, which is enough for a tool with no output schema. The only minor gap is that the interplay/optionality of 'lines' versus 'formula' is implied rather than stated.

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 67%, and the description compensates by explaining the two mutually exclusive input shapes (verbatim pasted text versus structured lines) and the unit rule (all lines in grams or all in percent). It also frames concentrationPct semantically ('how much of the finished product it may be', 'the concentration the user chooses'), which the schema only partially conveys.

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 (check) and object (a perfume or accord formula) plus the exact verdicts returned: IFRA compliance, finished-product percentage, which line to reduce, and EU allergens to declare. It is unmistakably distinct from sibling tools like get_material and find_starting_formula.

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?

Opens with a precise trigger ('when the user has a perfume or accord formula, pasted or drafted earlier in this conversation, and wants to know whether it is IFRA compliant...'). It also routes to alternatives explicitly: 'For one material's limit use get_material; for a starting recipe use find_starting_formula.'

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