Skip to main content
Glama

kiri_chat

Use this for any natural-language request that should search the catalog, check prices or PSA population, or work with a collection. The cost is usage-based and varies with complexity. Grades and PSA lookups it completes are charged at their listed prices. usage-based, holds $0.4212 per request, limited to 10 per minute and 100 per key per UTC day and 2 in flight.

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": {
      "message": "<message>"
    },
    "name": "kiri_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
backNoOptional back photo as a data:image/jpeg;base64,... URL
frontNoOptional front photo as a data:image/jpeg;base64,... URL
messageYesNatural-language request, up to 2000 characters
estimateNoWhen true, return a free cost range and the hold. Does not run Kiri.
thread_idNoOptional conversation id from an earlier kiri_chat response
max_cost_usdNoOptional cap in dollars, such as 0.25. A live request never charges more than this.
idempotency_keyNoUnique retry key

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and mostly delivers: it discloses usage-based cost that varies with complexity, pass-through charges for grades and PSA lookups, a $0.4212 per-request hold, and concrete rate limits (10/min, 100 per key per UTC day, 2 in flight). It does not cover failure behavior, whether the hold is released on error, or latency.

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

Conciseness3/5

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

The purpose is front-loaded and the cost/limit facts are useful, but the middle is garbled: 'usage-based' is stated twice ('The cost is usage-based and varies with complexity' then 'usage-based, holds $0.4212 per request'), and the sentence about grades and PSA listed prices reads as a fragment. Roughly a third of the text is redundant or malformed.

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?

An output schema exists, so return-value explanation is not required, and the description covers the two things an agent most needs before calling: cost model and rate/throughput limits. Gaps remain around error/hold-release behavior and how thread_id and idempotency_key should be used across retries, but the definition is broadly sufficient for a complex NL router.

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 seven parameters including estimate, max_cost_usd, thread_id and idempotency_key are already documented in the schema. The description adds only the general cost framing, which reinforces max_cost_usd indirectly but supplies no new syntax or constraint detail. Baseline 3 applies.

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

Purpose4/5

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

The description names the concrete jobs this tool covers: catalog search, price checks, PSA population lookups, and collection work, all driven by a natural-language message. That is a specific verb+resource framing that separates it from narrow structured siblings like get_prices or search_cards. It stops short of saying explicitly why an agent would pick this over those focused tools.

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?

'Use this for any natural-language request that should search the catalog, check prices or PSA population, or work with a collection' gives an implied rule (NL intent in, structured tool out), and the estimate flag hints at a free preview path. No sibling is named, no when-not condition is stated, and the existence of kiri_estimate leaves the cost-preview choice ambiguous.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources