best_vendors_forLive offers for one published compound, one best offer per vendor, sorted by price per mg ascending (blends and unpriceable products last). Prices are integer minor units plus display strings.
| Name | Required | Description | Default |
|---|---|---|---|
| compoundSlug | Yes | Compound slug, e.g. "retatrutide" |
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | ||
| offers | Yes | ||
| compound | Yes | ||
| compoundUrl | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false, and idempotentHint=true, so the safety profile is covered. The description adds valuable behavioral context: results are 'live', sorted by price per mg ascending, with blends and unpriceable products placed last, and prices are integer minor units plus display strings. This goes well beyond the annotations and helps the agent interpret results.
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 a single, dense sentence that packs in all essential details: live nature, one offer per vendor, sorting, placement of blends/unpriceable products, and price format. There is no fluff or repetition; every clause adds 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?
The tool is simple (one parameter, output schema exists), and the description covers the key behavioral aspects. It does not mention error cases (e.g., compound not found or not published), but the presence of an output schema likely defines return values. Given the low complexity and strong annotations, the description is nearly complete, just missing edge-case guidance.
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?
The input schema has 100% description coverage for the single parameter compoundSlug, providing an example. The description adds no additional parameter-specific meaning (e.g., format, constraints, or default behavior), so it meets the baseline but does not exceed it.
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 (best_vendors_for) and resource (a compound), and clarifies the result set: live offers, one per vendor, sorted by price per mg. This clearly distinguishes it from siblings like get_compound (compound details), list_vendors (vendor list), and search_compounds (compound search).
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 implies usage (when you want vendor offers for a specific compound) but does not explicitly contrast with alternatives or state when not to use it. It lacks phrases like 'for compound details use get_compound' or 'for all vendors use list_vendors', leaving the agent to infer context from sibling names.
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.
Each tool serves a clearly distinct purpose: search_compounds discovers compounds, get_compound retrieves compound details, best_vendors_for fetches offers for a compound, and list_vendors lists vendors. There is no meaningful overlap or ambiguity between them.
Three tools follow a clean verb_noun pattern (get_compound, list_vendors, search_compounds), but best_vendors_for breaks the pattern by using a descriptive phrase without a leading verb. Overall naming is still snake_case, readable, and mostly predictable.
Four tools is a well-scoped size for a read-only compound and vendor lookup server. Each tool covers a necessary function without redundancy or bloat.
The core workflows are covered: find a compound, get its details, see vendor offers, and view vendor trust information. Minor gaps exist, such as no browse-all-compounds endpoint and no individual vendor detail tool, but agents can work around these with the existing tools.