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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered. The description adds substantial context beyond that: products are counted at the maximum each label suggests, hidden-amount labels are flagged, fish oil is counted as EPA/DHA, and GB switches to NHS guidance. It stops short of stating rate limits or how ambiguous matches are resolved.

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 purpose, then examples, then input format, then return shape — a sensible order with no filler. It is somewhat dense and the prose runs long, but each sentence carries usable information.

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?

Though there is no output schema, the description enumerates the return fields (totals with contributing items and upper-limit/NHS comparison, other_totals, items, not_found) and covers edge cases like hidden label amounts and fish-oil EPA/DHA. An agent has everything needed to call it and interpret the result.

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% (baseline 3), but the description goes further: it specifies the semicolon separator, the 6-item cap, and that entries may be product names, barcodes, or amounts, plus the country=GB NHS behavior. This meaningfully extends the single schema line for 'items'.

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: it aggregates everything a person takes and checks the daily totals against adult upper limits. The 'up to 6 items' framing and the request examples ('is that too much?') clearly position it as a multi-item stack check, distinguishing it from the single-dose sibling check_dose.

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?

Provides two concrete triggering requests ('I take Centrum, vitamin D 5000 IU and zinc 50 mg, is that too much?' and 'is it OK to take OLLY Sleep with extra melatonin?') that make the use context obvious. It does not, however, name an alternative or state when-not to use it (e.g. single-item questions that check_dose handles).

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