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

The annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description instead adds real behavioural context: the density data is measured (not guessed), the corpus is 271 ingredients, and the response reports which cup definition was applied and cites the source. That last point is valuable output-behaviour disclosure in the absence of an output schema.

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?

The purpose and the ingredient-optional rule are front-loaded, and every other sentence does work. The single long unit enumeration is dense but earns its place because the unit parameters are free-form strings; still, it reads as a wall of nouns rather than a structured list.

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?

For a read-only five-parameter converter with a fully documented schema and no output schema, this covers the decision points an agent faces: which units exist, how cup ambiguity is resolved, when an ingredient is mandatory, and what the result reports about its own provenance. Only ingredient-name resolution failures are unaddressed, a minor gap against an otherwise complete picture.

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?

Coverage is 100%, so the baseline is 3, but the description goes further by enumerating the accepted unit vocabulary (including the six cup definitions and the spoon/fl-oz/butter-stick families) for free-form string parameters whose schema only supplies partial examples. It also reinforces that explicit units like metric_cup override cup_system, which is the subtlest interaction in the call.

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 sentence states a specific verb (converts) and a precise resource (a kitchen amount between volume and weight for a named ingredient), plus the data basis (USDA portion weights with FDC ids, King Arthur chart). This is unmistakably distinct from the sibling tools convert_oven_temperature, search_ingredients, and scale_recipe.

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 clearly establishes the condition that selects the ingredient parameter — "Volume to volume and weight to weight need no ingredient" — which is exactly the decision an agent needs to make. What it lacks is any routing to siblings, e.g. pointing at search_ingredients when the exact ingredient name is unknown.

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