API Plan Finder

Open an analysis canvas for the user

canvas_open

Use this when: the user is choosing an API plan and you want to show them the comparison on a page they can open, which you then steer with canvas_do. Before calling, ask the user for everything the comparison needs: what the API is for, the monthly volume, the budget, must-have conditions (billing, regions, concurrency, compliance) and what would be nice. Put every must-have you can into conditions (the same fields as search; budget as max_monthly_cost_usd, billing as billing_types); only conditions in these fields are checked. Returns canvas_url, the link to give the user, and a short summary: the shown plans with whether each meets every condition, where its cost sits among the shown plans (cost_band), the conditions it fails (fails) and the ones its provider does not state (not_stated). The exact costs, workings, sources and plan buttons are on the canvas only.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "conditions": "<conditions>",
      "user_goal": "<user_goal>"
    },
    "name": "canvas_open"
  }
}

Input Schema

Name	Required	Description
`offer_ids`	No	Plans the user already has in mind (offer ids from search or check_conditions): shown on the canvas whatever their verdict, two to four side by side.
`user_goal`	Yes	What the user wants, in their words. It is the canvas title.
`conditions`	Yes	Search fields, as for search.
`must_haves`	No	The user's must-have conditions in their words (shown on the canvas; put each one you can into conditions too).
`user_context`	No	Anything else the user said that matters (team, stack, deadline).
`nice_to_haves`	No

Output Schema

Name	Required	Description	Default
`shown`	Yes
`version`	Yes
`canvas_id`	Yes
`canvas_url`	Yes
`what_if_left`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 7, 2026

changedInput schema / properties / conditions / properties / preferred / description

Previous value: -"Nice-to-have conditions; they do not filter, they break ties."New value: +"Nice-to-have conditions; they do not filter, they break ties. Put a condition the person calls nice to have (\"would be good\", \"if possible\", \"되면 좋겠다\") here, not as a required field."

AddedNov 3, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations only say this is a non-read-only, non-destructive, non-open-world call; the description adds that it creates a user-openable page, that only conditions expressible in the listed fields are actually evaluated, and that detailed costs/sources live on the canvas rather than in the response. That last caveat is real behavioral disclosure. It spends some words restating the return shape, which the output schema already carries, so it stops short of 5.

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 'Use this when:' and ordered as trigger, prerequisites, field mapping, then returns, which is the right priority order. The sentences are long and clause-heavy, and the return-value sentence could be trimmed given the output schema, but almost every sentence carries real instruction.

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?

For a six-parameter tool with a deep nested conditions object and an output schema, the description covers the trigger, the data-gathering prerequisites, how to map user requirements into the conditions fields, and what comes back. Minor gaps remain around when to supply offer_ids versus providers and how nice_to_haves are used, but the essentials for a correct first call are present.

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?

With 83% schema description coverage and a very richly annotated nested conditions object, the schema already does most of the work. The description adds genuine mapping guidance ('budget as max_monthly_cost_usd, billing as billing_types', conditions are 'the same fields as search'), but leaves offer_ids, providers and nice_to_haves unaddressed, so it is helpful rather than complete.

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 concrete verb and artifact ('open an analysis canvas') plus the exact situation that calls for it, and names the companion tool canvas_do that then steers the same canvas. An agent can distinguish this from search or check_conditions without opening the 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 ('the user is choosing an API plan and you want to show them the comparison on a page') and a precondition ritual ('Before calling, ask the user for everything the comparison needs: ...'). It also routes follow-up interaction to canvas_do, so the relationship between the two tools is unambiguous.

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

All API Plan Finder 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?