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

Annotations cover the safety profile, and the description adds genuinely useful behavior the annotations cannot convey: every call is a 3-run consensus with disclosed spread and item agreement, the calibrated range contained truth in 26/30 weighed meals, and the cost is $0.05/image. Missing is any statement of what happens on failure/retry beyond the pack_code note in the 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?

Front-loaded with the core purpose in the first clause, followed by output contents, calibration evidence, consensus behavior and price. Three of the five sentences earn their place; the dense feature list ('PFC balance ratios and alcohol-aware 4/4/9 cross-checks') drifts toward marketing padding.

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?

An output schema exists, so return shape need not be re-explained, and the description still covers cost, consensus methodology and calibration honesty. The main gap is routing guidance relative to the many sibling extraction/OCR tools, which is not addressed at all.

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 the five parameters (hints, image_url, image_base64, x_payment, pack_code) are already fully documented in the schema. The description adds almost no parameter-level meaning beyond echoing that nutrition output is produced, so the 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?

States a specific verb and resource ('Analyze a meal photo to itemized nutrition JSON') plus an enumerated scope of outputs (dishes, portions, kcal, macros, confidence). That is clearly distinguishable from siblings like ocr_image, portrait_analysis and document_pipeline without opening any schema.

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?

Usage is only implied through the output description and the hints note ('measurably improves accuracy on regional home-style meals'). It never says when to pick this over ocr_image or structured_extract, and gives no exclusions or prerequisites beyond the payment mechanics that live in the schema.

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