Skip to main content
Glama

Aidoptio: AI adoption catalog, estimates and advisor tools

Benchmark Readiness Scan

benchmark_readiness
Read-onlyIdempotent

Six questions about one process: is it ready for a private evaluation benchmark on your own cases? Returns a 0-100 readiness score, what is already in place, what to prepare, and the fitting first step with its starting price (EUR excl. VAT). Same rule set as the scan on aidoptio.com. A transparent heuristic, not a measurement and not a quote. Deterministic: no model is called and the answers are not stored.

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": {
      "process": "<process>",
      "history": "<history>",
      "sensitivity": "<sensitivity>",
      "redlines": "<redlines>",
      "models": "<models>",
      "volume": "<volume>"
    },
    "name": "benchmark_readiness"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage of the returned text: en (English, default) or nl (Dutch).en
modelsYesHow do you use AI models or tools in this process today? none = Not yet; adhoc = Employees use general chat assistants ad hoc; pilot = A pilot or proof of concept with one model; production = In production, and we want to compare or switch models.
volumeYesWhat monthly volume do you want this process to handle? lt100 = Fewer than 100; 100-1000 = 100 to 1,000; 1000-10000 = 1,000 to 10,000; gt10000 = More than 10,000.
historyYesHow many historical cases with a known outcome can you pull? lt50 = Fewer than 50; 50-200 = 50 to 200; 200-1000 = 200 to 1,000; gt1000 = More than 1,000; unknown = I don't know yet.
processYesWhich process would you benchmark first? service = Customer service: tickets, e-mail, chat; cases = Case handling: claims, applications, dossiers; documents = Document intake and back office; sales = Sales: quotes, tenders, proposals; internal = Internal helpdesk: IT, HR, knowledge questions; undecided = Several candidates, not chosen yet.
redlinesYesAre there hard red-line rules the system must never break? written = Yes, written down in policies or procedures; tacit = Yes, but they live in our experts' heads; none = Not that we know of; unsure = I'm not sure.
sensitivityYesHow sensitive is the data in these cases? low = Low: mostly public or internal information; medium = Medium: customer data, can be pseudonymised; high-classified = High (health, financial, special categories), and classified; high-unclear = High, and nobody has classified it yet.

Output Schema

NameRequiredDescriptionDefault
rulesNo
scoreYes
pointsNo
answersNo
in_placeYes
disclaimerYes
max_pointsNo
to_prepareYes
recommendationYes
disclosures_urlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description discloses behavior an agent could not otherwise know: the scoring is deterministic with no model call, answers are not stored, the rule set matches the public website scan, and the output is a heuristic rather than a measurement or binding quote. These are exactly the facts that matter for a survey-style tool handling process and data-sensitivity details.

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?

The core question and the return contents are front-loaded in the first sentence, followed by short sentences on provenance, nature of the output, and privacy/determinism. No filler, no repetition of schema enums, and every sentence carries information the structured fields do not.

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?

Seven parameters with an output schema is moderate complexity, and the definition covers what the tool asks, what it returns, how it computes (deterministic heuristic, same rules as the website), and what it does with the data. An agent has everything needed to decide to call it and to set expectations about the response.

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% and every enum value is already documented, so the schema carries the parameter burden. The description still adds framing by characterizing the inputs as 'six questions about one process' — telling the agent all answers must describe a single process, which is a real constraint not expressed in the schema. It does not otherwise add format or validation detail.

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 a concrete assessment ('is it ready for a private evaluation benchmark on your own cases') and states exactly what comes back: a 0-100 score, current state, what to prepare, and a first step with starting price. That is specific verb+resource. It does not, however, distinguish itself from plausible siblings such as ai_literacy_scan or ai_act_triage, so an agent must infer the split from the name alone.

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 rather than stated: 'six questions about one process' and 'on your own cases' signal that this is an early, self-assessment step for one specific process. There is no explicit when-to-use/when-not, no prerequisites, and no named alternative for adjacent needs (literacy, AI Act triage, engagement estimate). The framing as 'not a measurement and not a quote' hints at boundaries but does not route the agent.

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