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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the baseline bar is low; the description still adds substantial context. It discloses the default listing behavior (up to 50 recent recipe names and IDs), that partial matches return candidates instead of guessed nutrition, and that absent values mean unknown rather than zero — all non-obvious traits an agent could otherwise misread.

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 critical constraint — read-only, no meal mutation — is front-loaded, and the sentence order moves from when-to-use to parameter selection to fallback listing to data interpretation caveats. It is dense and slightly long at seven sentences, but each sentence carries a distinct operative fact rather than 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?

For a zero-required-parameter read tool with an output schema present, the description covers everything an agent needs: purpose, triggering contexts, parameter selection logic, the no-parameter fallback, ambiguous-match handling, and how to interpret missing values. Return-format detail is correctly left to the output schema.

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%, so the baseline is 3, but the description adds real meaning: recipe_id is an exact ID match, name is a case-insensitive partial title search, and supplying neither triggers a listing. That clarifies the interaction between the two optional parameters better than the schema alone, which documents each in isolation.

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?

Opens with a specific verb and resource: 'Read saved recipe nutrition', immediately scoped by 'without logging or changing a meal'. That negative scope distinguishes it from any meal-writing sibling, so an agent knows this is a pure lookup of stored recipe facts rather than a diary operation.

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?

Gives concrete triggering situations: before answering questions about a saved recipe, checking previous meal macros, and follow-ups that challenge a recipe-based estimate. It also warns not to conclude macros are unavailable just because the profile holds only titles. It stops short of naming an alternative tool or an explicit when-not-to-use condition, so it is strong but not fully routing.

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