One foreign brand the person picked in the FineRx search — called by the card itself.
The same answer as find_us_equivalent for exactly that brand (its
``brandSlug`` from ui_suggest): the reviewed guidance, word for word, and
the US product only when it has the same active ingredient. Not for the model.
| Name | Required | Description | Default |
|---|---|---|---|
| locale | No | ||
| brand_slug | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey readOnlyHint, idempotentHint, and destructiveHint, so the description's burden is lower. The description adds meaningful behavioral context: the result mirrors find_us_equivalent exactly for that brand, guidance is returned word-for-word, and the US product is included only under the same-active-ingredient condition. There is no contradiction with annotations.
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 compact and front-loads the essential purpose, then adds the comparison to find_us_equivalent. The phrasing is somewhat cryptic ('called by the card itself', 'Not for the model') but every sentence earns its place, and the backtick-wrapped brandSlug reference is helpful.
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?
Given the simple two-parameter schema and helpful annotations, the description covers the key return behavior (guidance plus conditional US product) and the input provenance (brandSlug from ui_suggest). It lacks detail on locale semantics and error/edge cases, but it is adequate for a UI-helper tool.
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 compensate. It does clarify that brand_slug should come from ui_suggest's brandSlug value, which is useful. However, the optional locale parameter is never explained, leaving a gap for an otherwise undocumented parameter.
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 identifies the tool's role as returning the same result as find_us_equivalent for a specific foreign brand, including reviewed guidance word-for-word and the US product only when the active ingredient matches. It also clearly scopes it as a card/UI-level call ('called by the card itself'), distinguishing it from a general model-facing lookup. It lacks a crisp standalone verb phrase, relying on the sibling comparison plus annotations, so it is clear but not maximally self-contained.
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?
The description provides useful routing context: it names find_us_equivalent as the source of the same answer, specifies that the input comes from ui_suggest's brandSlug, and explicitly excludes the model ('Not for the model'). This implies when to prefer other tools, but it does not fully articulate alternate conditions such as 'use find_us_equivalent when the model needs this answer' or 'use another tool for other brands'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.