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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: how salts are counted as their mineral (estimated: true), how omega-3 is derived, how general names read one common label and say so, and that country=GB switches dose checks to NHS guidance. This is substantive disclosure, though it does not mention rate limits or auth needs.

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?

The description is long but front-loads purpose, then examples, then input rules, then the return shape, so the structure is sound. Most sentences earn their place by describing distinct output fields and edge cases, though it is denser than strictly necessary.

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?

There is no output schema, so the description must explain return values, and it does so thoroughly: dose_check with per_day_base, other_checks including blend-hiding cases, halal with its four states, alternatives, Amazon link, and halal_options. Nothing an agent needs 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 description coverage is 100%, so the schema already documents q, id, barcode and country. The description reinforces q/barcode and the GB/NHS effect on country, but adds little meaning the schema does not already carry. Baseline 3 is appropriate.

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 states a specific verb+resource: retrieve a supplement's label with per-serving amounts, dose check and halal status. It is distinguishable from most siblings by content. However, it never explicitly distinguishes itself from close siblings like supplementcheck_check_dose, check_stack or get_nutrient, so a 4 rather than a 5.

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 gives concrete triggering examples ("what's in Nature Made vitamin D3?", "is Centrum halal?") and states the accepted inputs (q or barcode), which implies usage. But it offers no guidance on when to prefer this over the sibling check_dose/check_stack tools and no exclusions, leaving selection partly to inference.

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