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

Annotations already establish read-only, non-destructive, closed-world behavior, and the description adds value on top: data sensitivity ('owner-private'), response content ('provenance and signed image views'), an auth requirement ('API key required') and a cost ('$0.02'). Cost and credential requirements are exactly the behavioral facts an agent cannot infer from the annotations.

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?

Four short sentences, front-loaded with the resource and scope, then the disambiguation, then the lookup hint, with cost/auth compressed into a trailing parenthetical. Every sentence earns its place; the telegraphic style ('owner-private Visual reference illustrations') is slightly dense but never padded.

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 an output schema covering return values, one fully documented parameter, and annotations covering safety, the remaining agent questions are access scope, cost and prerequisites — all answered in the description. Nothing needed to call it correctly 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 coverage is 100% and the single food_id property already documents that it comes from log_food or find_image_target and must not be duplicated. The description's 'existing food_id' and the find_image_target pointer largely restate that, adding little syntax or format meaning beyond the schema.

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 gives a specific verb and resource ('Read the ... Visual reference illustrations on an existing food_id') plus scope ('owner-private'), and explicitly separates it from the nearest confusion point ('Actual meal photos remain separate'). An agent can tell it apart from attach_food_photo, attach_food_visual_reference and get_visual_references without opening a 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?

It supplies a concrete prerequisite path ('Find the food_id using find_image_target') and pre-empts a likely misuse ('this read creates nothing'). What it lacks is an explicit exclusion against the similarly named get_visual_references or a statement of when no result is expected, so usage is clear but not fully bounded.

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