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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, but the description adds real behavior: "Nothing is logged" makes clear the read has no persistence side effect, and it lays out the correction-then-log workflow including the human-in-the-loop alternative of tapping Log on the card. The per-input-shape return behavior (plate, packet, scale) is behavior no annotation conveys.

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?

Roughly four sentences, all load-bearing: the trigger comes first, then what is returned, then the no-mutation + follow-up workflow, then the exclusions. No restatement of the title or 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 two-parameter tool with a nested photo object and an output schema, the description carries everything an agent needs: trigger, differentiated return shapes, the guarantee that nothing is persisted, and the exact follow-up call. Safety is covered by annotations and returns by the output schema, so 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?

With 100% schema description coverage, the schema already documents `photo` (the attached photo) and `note` ("half the rice", "oat flat white"). The description adds no syntax or format guidance for either parameter, so the baseline 3 applies; its explanatory energy goes to return shapes rather than inputs.

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 ("Reads" a food photo) and spells out what the read yields in three distinct cases: plate/bowl → per-food grams, calories, macros, confidence; packet → label per 100 g; pot on a scale → grams. An agent knows exactly what it gets back. It stops short of 5 because the near-identical sibling read_meal_photo_upload is never named or distinguished, leaving the attach-vs-upload boundary implicit.

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?

Clear positive condition ("when the person attaches a photo of food they ate or will eat") and explicit exclusions ("Do not use for a photo that isn't food, or to judge anyone's body"). It also names the correct next step, log_foods with its logItems. The one gap is that the closest alternative, read_meal_photo_upload, is not mentioned as the route for a different photo source.

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