Skip to main content
Glama

Aidoptio: AI adoption catalog, estimates and advisor tools

Plan an AI vendor evaluation on your own cases

plan_vendor_evaluation
Read-onlyIdempotent

For a buyer choosing between 2 and 8 AI vendors. Returns weighted criteria (sum 100), a test plan on your own cases (typical, edge and red-line cases; red lines pass only with zero violations), data-route rules for the sensitivity you give, a preregistration (canonical JSON plus SHA-256 method hash) to freeze before the first vendor run, six questions to ask any advisor (us included), Aidoptio's own disclosure for this shortlist, and one fitting next step. The plan works without Aidoptio. Case numbers are an Aidoptio method default, not a scientific norm; a plan, not a measurement and not legal advice. Deterministic: same input, same hash. Vendor names are part of the hash and are not stored. monthly_volume is validated but does not change the plan.

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": {
      "use_case": "<use_case>",
      "vendors": "<vendors>",
      "data_sensitivity": "<data_sensitivity>"
    },
    "name": "plan_vendor_evaluation"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage of the returned text: en (English, default) or nl (Dutch).en
vendorsYesNames of the vendors on the shortlist. Order does not matter for the hash.
use_caseYesThe process the vendors are evaluated for: service (customer service), cases (case handling), documents (document intake and back office), sales, internal (internal helpdesk) or other.
red_linesNoRules a system must never break, e.g. "Never promise a refund".
prioritiesNoWeight per dimension: high, normal (default) or low.
monthly_volumeNoCases per month, roughly. Optional.
data_sensitivityYeslow (public or internal), medium (customer data, can be pseudonymised), high-classified (health, financial or special categories, and classified) or high-unclear (high, not classified yet).

Output Schema

NameRequiredDescriptionDefault
rulesNo
criteriaYes
next_stepYes
test_planYes
data_routeYes
disclaimerYes
policy_versionYes
disclosures_urlYes
preregistrationYes
advisor_checklistYes
aidoptio_disclosureYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations: it discloses determinism and hash stability across identical inputs, that vendor names feed the hash but are not stored, that monthly_volume is validated yet has no effect on the plan, and that red lines only pass with zero violations. It also frames the case counts as a method default rather than a scientific norm, which is exactly the kind of caveat an agent needs to relay.

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 the audience and the payload list, and nearly every clause carries distinct information. It is one dense block rather than separated output items, which makes it slightly harder to scan, but there is no filler sentence to cut.

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?

With an output schema present the description need not describe return values, and annotations already cover the safety profile, so the remaining burden is caveats and limits — determinism, non-persistence of vendor names, the inert optional parameter, and the non-legal-advice framing are all covered. Nothing an agent needs to call or represent the result correctly is missing.

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%, so the baseline would be 3, but the description adds meaning the schema does not: vendor order is irrelevant to the hash, names are not persisted, data_sensitivity drives the data-route rules, and monthly_volume is inert. The only remaining gap is that it does not explain how priorities weightings interact with the fixed 100-sum criteria, which the schema also leaves unexplained.

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 and resource ('plan_vendor_evaluation' for 'a buyer choosing between 2 and 8 AI vendors') and then enumerates the concrete artifacts returned: weighted criteria summing to 100, a test plan with typical/edge/red-line cases, data-route rules, a preregistration with SHA-256 method hash, advisor questions, and a next step. An agent can tell this apart from measurement or triage siblings 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 Guidelines4/5

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

Gives a clear trigger condition (a buyer shortlisting 2–8 AI vendors) and explicit exclusions: it is 'a plan, not a measurement and not legal advice', and 'the plan works without Aidoptio'. It does not name a specific sibling tool to use instead when the user actually wants a measurement or readiness check, so routing among siblings is left partly implicit.

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