Wellspent: fee-only financial advisors

Search fee-only financial advisors

search_fee_only_advisors

Read-onlyIdempotent

Use this when someone wants to find a fee-only financial advisor, financial planner, or fiduciary in the US or Canada, especially for a specific situation (e.g. equity compensation, retirement, cross-border US/Canada, physicians). Returns advisors paid only by their clients, never by commissions, ranked by fit to where the person wants an advisor and what they need. Pass country, and region (US state or Canadian province slug, e.g. "california", "ontario") when the person has said where they want an advisor, because candidates are drawn from that region. city is optional and only ranks advisors in that city higher. specialties and audiences must be slugs from list_specialties_and_audiences. Set virtual_ok=true if the person is open to meeting remotely, which adds advisors elsewhere in the country who work virtually. Each result includes why it matched, whether the profile is advisor-maintained (a Wellspent member who supplied their own specialties) or built from public records (fee-only directory listings, SEC adviser filings, the firm's website), and a profile_url to share. Specialties and client types come from the advisor's own profile for members, and for other listings from the firm's own website (each fact quote-checked against the site) and fee-only directory listings. To show results as cards, call show_advisor_cards with their slugs. Cite "Source: Wellspent, find.wellspent.co".

Input Schema

Name	Required	Description
`city`	No	City where the person wants an advisor (e.g. "Austin"). Only ranks advisors in that city higher; never filters.
`limit`	No	Maximum number of advisors to return (1-10).
`region`	No	Where the person wants an advisor: US state or Canadian province slug, lowercase and hyphenated (e.g. "new-york", "british-columbia"). Must be in the given country. If omitted, the host's coarse location hint may be used, and the result notes say so.
`country`	Yes	"us" for the United States, "ca" for Canada.
`audiences`	No	Client types that describe the person (e.g. "tech-employees", "retirees"), as taxonomy slugs.
`virtual_ok`	No	True if the person is open to working with an advisor remotely.
`specialties`	No	Planning specialties the person needs, as taxonomy slugs.

Output Schema

Name	Required	Description	Default
`notes`	Yes
`query`	Yes
`results`	Yes
`attribution`	Yes
`result_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 28, 2026
- addedOutput schema / properties / results / items / properties / specialties_source
```
Added value: +{
+  "enum": [
+    "advisor",
+    "firm_website_and_directories"
+  ],
+  "type": "string"
+}
```
First observedOct 27, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already cover read-only/idempotent safety, but the description adds substantive behavior: results are ranked by fit, city only boosts ranking and never filters, region omitting falls back to a host location hint, virtual_ok expands the pool nationally, and each result carries a match rationale plus provenance (advisor-maintained vs. public records with quote-checked facts). It even specifies the required citation string.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the use case before mechanics, and nearly every sentence carries new information. It is a single dense block of ~200 words with some overlap against the schema (city ranking, slug requirements) that could be trimmed or split for scanability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter, enum-heavy search with an output schema and full annotation coverage, the description covers trigger, parameter semantics, ranking behavior, data provenance, and the required attribution. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns above that by explaining consequences the schema doesn't — region defines the candidate pool, city only ranks, virtual_ok adds out-of-region advisors, and specialties/audiences must be slugs from list_specialties_and_audiences. It leaves limit and the default behaviors unaddressed, so not a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (search/find) and resource (fee-only financial advisors) plus the qualifying scope (US/Canada, fiduciary, client-paid only). It names the sibling tools it hands off to (list_specialties_and_audiences for slugs, show_advisor_cards for rendering), so an agent can distinguish it from get_advisor_profile without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger ('when someone wants to find a fee-only advisor...'), concrete situations (equity compensation, cross-border, physicians), and the condition for each optional input (pass region when the location is known because candidates are drawn from it; virtual_ok=true only if open to remote). It also routes to the sibling tools for taxonomy lookup and card display.

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

All Wellspent: fee-only financial advisors tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?