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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so "Read-only" is redundant, but the description adds a genuinely non-structural trait: the output is an approximation from USDA data and may contain unmatched ingredients that must be surfaced. That partial-match caveat is exactly the kind of behavioral context annotations cannot convey; only the lack of detail on what unmatched means or how large the error can be keeps it from a 5.

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 purpose, then the caveat, then the return shape in a single compact block with zero filler. "Read-only" is the only wasted clause since the annotations already say it, and it is one word.

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 steps in to sketch the return shape (`per_serving`, `total`, `matched`, `unmatched`), and it flags the accuracy caveat an agent needs in order to report results honestly. For a two-parameter read tool with full schema coverage, nothing material 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 description coverage is 100%, so both `id` (including its provenance from search_recipes) and `servings` (including the default) are already fully documented in the schema. The description adds only the framing that results are reported per-serving and in total, which is return-shape context rather than parameter meaning, so baseline 3 applies.

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?

"Estimate nutrition for one recipe" is a specific verb+resource, and the description immediately scopes the aggregation ("per serving and total") and the data source (USDA). It also bounds the input to "one recipe the user can see," which separates it from any hypothetical batch/plan-level nutrition operation among the 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?

"One recipe the user can see" gives a clear precondition, and the instruction to tell the user it is an estimate and mention unmatched ingredients is actionable usage guidance for the response. It stops short of naming an alternative tool or stating when not to call it, but no sibling exposes nutrition at all, so the routing risk is low.

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