One regulation: what it is, its jurisdiction and scope, a link to the law itself, and reaches[] — the country, region and industry cohorts this regime binds. Use reaches[] to go straight to the affected members with find_providers.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Regulation slug, as find_regulations returns it, e.g. "21-cfr-part-11". | |
| context | No | Optional: one sentence on why you are asking. Never used to rank; read only if a result is wrong. |
Changes observed during successful MCP inspections.
Input schema / properties / context / descriptionPrevious value: -"Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."New value: +"Optional: one sentence on why you are asking. Never used to rank; read only if a result is wrong."Input schema / properties / slug / descriptionAdded value: +"Regulation slug, as find_regulations returns it, e.g. \"21-cfr-part-11\"."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. Beyond that, the description discloses the shape and meaning of the returned content, notably that reaches[] holds the country/region/industry cohorts the regime binds — context the annotations cannot supply. It omits error behavior for an unknown slug and any note on how complete the law link or scope fields are.
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?
Two sentences, no filler, front-loaded with the object being fetched. The first sentence is a dense field list but each item is informative; the second earns its place by turning the output into an action.
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?
For a read-only single-entity lookup with no output schema, an agent needs to know the returned fields and how to use them — both present. What remains unstated is failure behavior (bad/unknown slug) and whether the law link and reaches[] are always populated.
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 both the required slug (with example '21-cfr-part-11') and the optional context parameter are already documented in the schema. The description adds no parameter-level detail beyond that, which is the expected baseline when the schema does the heavy lifting.
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 names the specific resource ('One regulation') and enumerates the payload an agent will get back: identity, jurisdiction, scope, a link to the law, and reaches[]. The singular framing implicitly contrasts with the plural find_regulations search tool, but it never names that sibling explicitly, so differentiation is inferred rather than stated.
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 a concrete next-step rule: 'Use reaches[] to go straight to the affected members with find_providers.' That is real routing guidance for what to do with the result. It does not, however, say when to prefer this over find_regulations (e.g., when you already have a slug), which is the more common selection decision.
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.