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

Well beyond the readOnly/idempotent/destructive annotations, it discloses determinism, no outbound calls, no price lookups, no persistence, per-call pricing ($0.002 via x402, USDC on Base) and that 400/422 responses are not charged. Those billing and side-effect details are exactly the behavior an agent cannot infer from annotations.

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?

It is a single dense paragraph, but purpose and input shape are front-loaded and every clause (output fields, error handling, pricing) carries information an agent needs. It reads as a run-on rather than cleanly separated sections, which costs it a point.

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 no output schema, the description enumerates the return payload (name, canonicalId, qty, unit, metric, category, optional/toTaste, prepNote, pack size/hint, merged shoppingList, unparsed lines) and covers failure modes and cost. Nothing needed to call or interpret the result 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 already 100%, so the baseline is 3, but the description adds real meaning: the alternate GET query form (ingredients=line|line), the coupling of servings with targetServings, and the envelope shape of the POST body. It does not add per-parameter limits beyond the schema's max 100 lines / 200 chars.

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 opening phrase 'Recipe to shopping list normalizer' names a specific verb (normalize) and resource (recipe ingredients → shopping list) rather than restating the vague tool name. It immediately distinguishes the tool from every sibling, which are all payment/infra/fetch utilities.

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?

It gives concrete invocation patterns — POST JSON with {ingredients, servings?, targetServings?} or GET with ingredients=line|line — and notes that servings must be paired with targetServings to scale. It does not state any when-not-to-use condition, but there is no sibling that overlaps functionally, so guidance is effectively complete.

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