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

Goes beyond the read-only/idempotent/closed-world annotations by disclosing the scoring model (0-100 Greener Closet score, synthetic share, main concerns) and an important edge case: mismatched percentages yield the gap instead of a score. That edge-case behavior is exactly the kind of failure mode an agent needs forewarned. Minor deduction since prompt-side input normalization (e.g. handling unsorted or unit-less text) is not discussed.

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 triggering case and followed by examples, exclusions, and return behavior in a logical order. It runs long for one paragraph with two quoted example inputs, but each sentence (including the percentage-gap rule) carries information an agent would otherwise have to guess.

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?

An output schema exists, so return structure needn't be restated, and the description nevertheless summarizes the outputs and the no-score fallback. For a single-parameter, closed-world read tool, nothing needed to call it 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% and the single parameter is already documented, so the baseline is 3. The description adds value by showing several accepted input forms (percent+percent, percent+% fiber, with organic/recycled modifiers), which clarifies that free-form label text is fine rather than requiring a normalized format.

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 object (check a fabric label / fiber composition) with concrete input examples like "60% cotton, 40% polyester". It also names what it is not (check_product for URLs, explain_fiber for single-fiber questions), so an agent can route correctly against all siblings.

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 triggering condition (user supplies composition or care-label text and asks whether it's good/sustainable/synthetic/better than another), plus a worked comparison workflow: 'To compare labels, call it once per label.' Exclusions to check_product and explain_fiber are named directly.

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