IA-QA — 152 QA & Dev Tools for AI Agents

token_budget_calculator

Read-onlyIdempotent

Plan token allocation across system prompt, user input, context/RAG chunks, and expected output. Warns if budget exceeds the model's context window (any model from list_llm_models).

Input Schema

Name	Required	Description
`model`	Yes	Model id from list_llm_models (e.g. gpt-6.1-sol, claude-sonnet-5-5, gemini-3.8-flash)
`context`	No	Actual context text (will estimate tokens)
`user_input`	No	Actual user input text (will estimate tokens)
`system_prompt`	No	Actual system prompt text (will estimate tokens)
`context_tokens`	No	Token count for RAG context / documents
`user_input_tokens`	No	Token count for user message
`system_prompt_tokens`	No	Token count for system prompt
`expected_output_tokens`	No	Expected max output tokens

Output Schema

Name	Required	Description	Default
`model`	No
`warnings`	No
`breakdown`	No
`context_window`	No
`fits_in_window`	No
`remaining_tokens`	No
`utilization_percent`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedInput schema / properties / model / description

Previous value: -"Model name (e.g. gpt-4o, claude-3.5-sonnet, gemini-3.5-flash)"New value: +"Model id from list_llm_models (e.g. gpt-6.1-sol, claude-sonnet-5-5, gemini-3.8-flash)"

Changed1 schema field changedOct 31, 2026

addedInput schema / examples

Added value: +[
+  {
+    "context_tokens": 1000,
+    "expected_output_tokens": 500,
+    "model": "gpt-4o"
+  }
+]

Changed1 schema field changedOct 26, 2026

changedInput schema / properties / model / description

Previous value: -"Model name (e.g. gpt-4o, claude-3.5-sonnet, gemini-2.0-flash)"New value: +"Model name (e.g. gpt-4o, claude-3.5-sonnet, gemini-3.5-flash)"

Changed1 schema field changedJun 21, 2026

addedOutput schema / properties

Added value: +{
+  "breakdown": {
+    "type": "object"
+  },
+  "context_window": {},
+  "fits_in_window": {},
+  "model": {},
+  "remaining_tokens": {},
+  "utilization_percent": {},
+  "warnings": {}
+}

Changed1 schema field changedJun 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

First observedMay 26, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful behavior by stating that it warns when the budget exceeds the model's context window and that models come from list_llm_models. It does not explain token estimation from raw text or output behavior, though an output schema exists.

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?

Two sentences, front-loaded with the core purpose and followed by the key warning behavior. There is no redundant or filler text.

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?

The tool has rich structured context: full schema coverage, annotations, and an output schema. The description covers the purpose and warning condition adequately. A minor gap is that it does not clarify the text-vs-token input modes, but the schema handles that.

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 the schema already documents all eight parameters, including the text-vs-token-count alternatives. The description reinforces the allocation categories and model source but adds no syntax or format details beyond the schema. Baseline 3 is appropriate.

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 states a specific verb and resource: planning token allocation across system prompt, user input, context/RAG chunks, and expected output. It also mentions the warning behavior for exceeding the model's context window. It does not explicitly contrast itself with siblings like count_tokens or context_window_check, so it falls short of a 5.

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?

Usage is implied by the planning and budget-warning framing, and the description points to list_llm_models for valid model IDs. However, it gives no explicit when-to-use guidance versus count_tokens, context_window_check, or estimate_llm_cost, and no exclusions.

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

All IA-QA — 152 QA & Dev Tools for AI Agents 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.