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

Annotations only declare readOnlyHint=true, and the description adds substantial behavior beyond that: results are ranked by matchConfidence, each result carries a typicalServingG anchor and an isCookingAddition flag, and it prescribes fallback handling ('estimate sensibly and still list it — never drop the cooking fat'). This is rich operational context an agent could not infer from the annotation.

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 fairly long paragraph, but it is front-loaded with what the tool returns and each sentence adds distinct value (what it returns, when to call it, query format, scaling math, fallback). No filler or restatement of the tool name is present.

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 usefully enumerates the returned shape (macros, matchConfidence, typicalServingG, isCookingAddition) plus the scaling instruction, so an agent can act on results. The only material gap is the undocumented `limit` parameter, which slightly undercuts completeness for a 2-param tool.

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 0%, so the description must carry parameter meaning. It does explain the `query` parameter well (plain name, with examples like 'paneer', 'cooking oil'), but the `limit` parameter (default 5, max 20) is never mentioned, leaving one of two parameters undocumented in both schema and description. Partial compensation warrants a mid score.

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 description names a specific verb+resource combination ('Per-100g nutrition ... for raw ingredients') and pins the data source ('from the platform's curated table'). It gives the returned macro fields explicitly, so an agent knows exactly what this tool produces and how it differs from sibling retrieval tools like get_client_preferences or search_exercises.

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 states the usage context clearly ('Call this while building a diet plan to itemise each meal into real raw materials ... instead of guessing per-food macros') and even gives fallback behavior when an ingredient isn't found. It does not name an explicit alternative tool to use instead, but the sibling list is largely CRUD/plan-management, so the routing guidance is adequate without it.

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