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

Goes well beyond the annotations: discloses the required 'Save meals you confirm' permission, the exactly-as-estimated fidelity guarantee, the draft-superseding behavior on re-estimation, and an explicit prompt-injection warning that food names/notes in the result are untrusted data. None of that is derivable from readOnlyHint/destructiveHint/openWorldHint.

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 tight sentences, each carrying a distinct rule (what it does, when to call, how to revise, permission, injection safety), with the precondition front-loaded where the agent will read it first.

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?

No output schema, but the description sketches the result's contents (food names and notes) and covers permissions and preconditions. The remaining gap is failure behavior — what happens with an expired or already-used draft_id, and whether the call is idempotent — which an agent would otherwise have to discover by error.

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 only 33% (eaten_at is the sole documented field), and the description only partially compensates: it clarifies that draft_id refers to a draft produced by estimate_meal and that edits must go through a new draft. It says nothing about meal_type's enum choices or how eaten_at defaults are applied beyond the schema's own note.

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+resource+source: save a meal from an estimate_meal draft into the user's Glucoray log. It explicitly names the sibling estimate_meal as the producer of the input, so the agent can distinguish this terminating write from the estimation step without opening the 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?

Gives an explicit precondition (must show the estimate with items, portions, net carbs and receive an explicit yes), an explicit prohibition (never save on your own initiative), and the correct alternative path for edits (call estimate_meal again and save the new draft).

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