get_food_details

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower. The description adds genuine behavioral context: the returned `nutrients` are keyed and scaled exactly as add_custom_food/update_custom_food take them, so values can be read and written back unchanged, and it notes Cronometer's own per-100g rows come alongside. No rate limits or caching noted, but this is above the annotation baseline.

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, then workflow, then the round-trip detail, then the arg. The `nutrients` keying explanation is dense but earns its place by preventing a format mismatch. Minor redundancy with the Args block, but no 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?

With one parameter, rich annotations, and an existing output schema, the description is nearly complete: it covers purpose, workflow position, parameter source, and even the return shape. Only explicit edge-case or freshness behavior (caching, staleness) is absent, a minor gap.

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 0%, so the description must carry the burden. It documents the single required parameter by origin: 'Food ID from search_foods results', which tells the agent exactly where to obtain a valid id rather than just echoing the name.

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 ('Get detailed food information including nutrition and serving sizes') and distinguishes itself from siblings by naming search_foods as the upstream source and add_food_entry as the consumer. An agent can tell this apart from get_food_log or list_custom_foods 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?

'Use this after search_foods' gives clear workflow context and names the reason (full nutrient profile plus measure_ids needed for add_food_entry). It stops short of explicit when-not guidance or edge cases, but the ordering relative to alternatives is unambiguous.

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