Skip to main content
Glama

costkits-mcp

by io.github.costkits
OverviewDiscussionsAdmin

find_providers

Read-only

Lists up to 5 facilities in one US state that perform a procedure, with name, address and a pricing_status field: 'observed' means a negotiated rate is published in that facility's price transparency data, 'estimated' means only a state-level benchmark applies, 'none' means no price data. Dollar amounts are not returned. The list is partial and is not a ranking or a recommendation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax results, 1 to 5 (default 5)
stateYes2-letter US state code, e.g. 'CT'
procedureYesProcedure slug or plain name, e.g. 'colonoscopy'

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • removedInput schema / properties / cluster
      Removed value: -{
-  "description": "Group by city with lat/lng (default false)",
-  "type": "boolean"
-}
    • changedInput schema / properties / limit / description
      Previous value: -"Max results (default 25)"New value: +"Max results, 1 to 5 (default 5)"
    • changedInput schema / properties / limit / maximum
      Previous value: -100New value: +5
    • changedInput schema / properties / procedure / description
      Previous value: -"Procedure slug or plain name"New value: +"Procedure slug or plain name, e.g. 'colonoscopy'"
    • changedInput schema / properties / state / description
      Previous value: -"2-letter US state code"New value: +"2-letter US state code, e.g. 'CT'"
  2. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses crucial behavioral traits: dollar amounts are NOT returned, the list is partial, and it is explicitly not a ranking or recommendation. It also defines the pricing_status enumeration semantics ('observed' vs 'estimated' vs 'none'), which is exactly the kind of value semantics annotations cannot carry.

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

Conciseness5/5

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

Three tight sentences with zero filler; the core behavior is front-loaded and the caveats (no dollar amounts, partial list) follow in priority order. Every sentence carries information an agent needs.

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

Completeness4/5

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

With no output schema, the description carries the return-value burden well, naming the returned fields and explaining pricing_status. It is slightly incomplete on failure modes (e.g., unknown procedure slug, and the existence of resolve_procedure as a prerequisite) and on ordering/pagination behavior.

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

Parameters3/5

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

Schema description coverage is 100%, so all three parameters are already documented in the schema, giving a baseline of 3. The description reinforces the limit (up to 5) and single-state scope but adds no format or syntax detail beyond the schema.

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 (Lists), resource (facilities/providers), and scope (up to 5 in one US state that perform a procedure), plus the exact return fields. An agent can distinguish it immediately from the singular get_provider and from pricing tools like estimate_procedure_cost without opening any schema.

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

Usage Guidelines3/5

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

Scope is implied ('up to 5', 'one US state') but there is no explicit when-to-use guidance and no alternative named, even though siblings like get_provider, estimate_procedure_cost, and resolve_procedure overlap in the provider/cost domain. The agent must infer that this is a discovery/shortlist call rather than a pricing call.

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

All costkits-mcp toolsInspect
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