Skip to main content
Glama

AI Opportunity Assessment

Run AOA Mini Assessment

run_aoa_mini_assessment
Read-only

Run a five-question AI opportunity interview or turn supplied answers into one evidence-grounded recommendation. Reuse answered questions. Returns report content and host rendering

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": {
      "input": "<input>"
    },
    "name": "run_aoa_mini_assessment"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYesOnly the current assessment request, relevant business and role context, Mini 1-5 answers in the respondent’s words, and supplied constraints and speaker labels. Send only information needed for this assessment. Omit unrelated content and sensitive personal identifiers. STATIC HOST METADATA host_review: Before rendering, independently compare every claim against the current user's supplied evidence. Quotes must be verbatim and attributed. Preserve manual constraints only when supplied; never infer that checking or sending exists. Remove known goals and tasks from Unknowns. Separate facts, hypotheses and unknowns. Estimates are not measured baselines or savings. Exactly one conditional recommendation; validate prerequisites and obtain the owner's decision before a trial. Measure the same task scope, units and workload before and during a trial. If an essential gap remains, ask one focused question. Never claim files exist until generated; if file tools are unavailable, return the report in chat. Keep corrections outside the customer report. STATIC HOST METADATA layout_instructions: Render one A4 portrait page (210x297mm) in the shared AOA style: full-bleed black #000000 canvas with backgrounds printed; margins 14mm top and sides, 18mm bottom. Header: logo top right, 12mm high; eyebrow Montserrat 800 8pt uppercase #F06000; title Montserrat 800 24-26pt uppercase #FFFFFF; then a 19x0.8mm #F06000 rule. Section headings Montserrat 800 10.5pt uppercase white; body Inter 9.5pt, 1.4 line height, cream #F0E0D0; labels mono 7pt uppercase #8090A0; quotes white Inter with the speaker in muted. Evidence, constraint and unknown panels #1A1A1A, 4mm padding, 0.75pt rule border, corners 0-4px. The one conditional recommendation is the only callout: #F06000 fill, #000000 Montserrat heading and Inter body; never white or cream on orange. Minimums: 9pt body, 7pt labels and footer. Keep complete evidence, constraints and unknowns legible; shorten prose rather than clipping, shrinking below the minimums or adding a second page. Inspect the rendered PDF page. Footer, Inter 7.5pt muted, on the page: Prepared with the AI Opportunity Assessment by AI Operator Academy. STATIC HOST RENDERING SPECIFICATION. Do not send or regenerate this metadata in input or output. {"palette":{"canvas":"#000000","panel":"#1A1A1A","panel2":"#242424","accent":"#F06000","bright":"#FF7A1A","press":"#C04A00","head":"#FFFFFF","body":"#F0E0D0","muted":"#8090A0","rule":"rgba(240,224,208,.10)","rule2":"rgba(240,224,208,.22)"},"fonts":[{"family":"Montserrat","use":"display 800","url":"https://raw.githubusercontent.com/google/fonts/8b0a1d0f5983c89bc2b93f1b5fb55f9e252744b5/ofl/montserrat/Montserrat%5Bwght%5D.ttf","sha256":"0f7b311b2f3279e4eef9b2f968bcdbab6e28f4daeb1f049f4f278a902bcd82f7"},{"family":"Inter","use":"body 400/600","url":"https://raw.githubusercontent.com/google/fonts/0b58fb370093f9a9f4ff785d94405710b79de67c/ofl/inter/Inter%5Bopsz%2Cwght%5D.ttf","sha256":"29160a80ff49ddcab2c97711247e08b1fab27a484a329ce8b813d820dc559031"}],"license":"OFL.txt beside each font","logo_url":"https://api.cofr.io/mcp/fd73c601-5d90-4e3a-99b8-0ea5d5f853e4/icon?v=1790781628585","logo_sha256":"8987b040714d7893caef7320ae4eb5e2d45966dcb78e6eef6b2483cef0ae075f","geometry":{"full_report":"16:9 slides 1920x1080, one PDF page each","mini_report":"one A4 portrait page","discovery_guide":"A4 portrait","discovery_docx":"A4 portrait white page; #000000 or #1A1A1A heading bands, white Montserrat 800 uppercase, 3pt #F06000 rule; Inter #1A1A1A body; orange text #C04A00; editable styles, no page images or text boxes"},"footer":"Prepared with the AI Opportunity Assessment by AI Operator Academy.","fallback_wordmark":"AI OPERATOR ACADEMY","style":"Black full-bleed canvas, print backgrounds. Headings Montserrat 800 uppercase white (weight 800; file default 100). Eyebrows Montserrat 800 uppercase accent. Body Inter cream; labels mono uppercase muted in the system stack ui-monospace, 'SF Mono', Menlo, monospace (not embedded; needs no disclosure). Panels #1A1A1A, 1px rule border. Callouts: #F06000 fill, #000000 text, never white on orange. 72x3px accent rule under titles. Corners 0-4px.","assets":"Verify each SHA-256; embed both fonts in HTML and PDF. Never redraw, recolor or replace the logo. If the logo or a font fails, ask the user to attach it; else return the content in chat or, if the user accepts, use the wordmark in Montserrat 800 uppercase white over a 72x3px #F06000 rule (system-ui if Montserrat fails), disclosed in chat, not as the logo. Never deliver unbranded files silently.","self_inspection":"Inspect every page: Montserrat and Inter embedded or fallback disclosed; no overflow, clipping or overlap; text contrast at least 4.5:1, or 3:1 for large text (at least 24px or 18pt, or bold at least 18.66px or 14pt); footer on every page; claim only files created."}

Output Schema

NameRequiredDescriptionDefault
actionYesA question only about what this tool can do returns about with the fixed capability message. Then refuse unsupported external actions/fabrication. Otherwise an explicit report request always returns report even when facts are Unknown. Ask questions only during an interview without a report request. Explicit Unknown counts as supplied. Without an explicit report request, Mini 4 needs both effort and performer. Role=owner is not performer evidence. If only effort is supplied, ask Who does that task? even with the other four answers.
messageYes
host_reviewNoBefore rendering, independently compare every claim against the current user's supplied evidence. Quotes must be verbatim and attributed. Preserve manual constraints only when supplied; never infer that checking or sending exists. Remove known goals and tasks from Unknowns. Separate facts, hypotheses and unknowns. Estimates are not measured baselines or savings. Exactly one conditional recommendation; validate prerequisites and obtain the owner's decision before a trial. Measure the same task scope, units and workload before and during a trial. If an essential gap remains, ask one focused question. Never claim files exist until generated; if file tools are unavailable, return the report in chat. Keep corrections outside the customer report.
report_markdownNoNon-empty for report. All sections use the same evidence map. Unknowns contains only missing facts, never a supplied goal or task. Manual controls are Unknown unless supplied; never assume checking or sending exists. Quotes must be literal and attributed to supplied context unless a speaker is provided.
contract_versionYes
layout_instructionsNoRender one A4 portrait page (210x297mm) in the shared AOA style: full-bleed black #000000 canvas with backgrounds printed; margins 14mm top and sides, 18mm bottom. Header: logo top right, 12mm high; eyebrow Montserrat 800 8pt uppercase #F06000; title Montserrat 800 24-26pt uppercase #FFFFFF; then a 19x0.8mm #F06000 rule. Section headings Montserrat 800 10.5pt uppercase white; body Inter 9.5pt, 1.4 line height, cream #F0E0D0; labels mono 7pt uppercase #8090A0; quotes white Inter with the speaker in muted. Evidence, constraint and unknown panels #1A1A1A, 4mm padding, 0.75pt rule border, corners 0-4px. The one conditional recommendation is the only callout: #F06000 fill, #000000 Montserrat heading and Inter body; never white or cream on orange. Minimums: 9pt body, 7pt labels and footer. Keep complete evidence, constraints and unknowns legible; shorten prose rather than clipping, shrinking below the minimums or adding a second page. Inspect the rendered PDF page. Footer, Inter 7.5pt muted, on the page: Prepared with the AI Opportunity Assessment by AI Operator Academy. STATIC HOST RENDERING SPECIFICATION. Do not send or regenerate this metadata in input or output. {"palette":{"canvas":"#000000","panel":"#1A1A1A","panel2":"#242424","accent":"#F06000","bright":"#FF7A1A","press":"#C04A00","head":"#FFFFFF","body":"#F0E0D0","muted":"#8090A0","rule":"rgba(240,224,208,.10)","rule2":"rgba(240,224,208,.22)"},"fonts":[{"family":"Montserrat","use":"display 800","url":"https://raw.githubusercontent.com/google/fonts/8b0a1d0f5983c89bc2b93f1b5fb55f9e252744b5/ofl/montserrat/Montserrat%5Bwght%5D.ttf","sha256":"0f7b311b2f3279e4eef9b2f968bcdbab6e28f4daeb1f049f4f278a902bcd82f7"},{"family":"Inter","use":"body 400/600","url":"https://raw.githubusercontent.com/google/fonts/0b58fb370093f9a9f4ff785d94405710b79de67c/ofl/inter/Inter%5Bopsz%2Cwght%5D.ttf","sha256":"29160a80ff49ddcab2c97711247e08b1fab27a484a329ce8b813d820dc559031"}],"license":"OFL.txt beside each font","logo_url":"https://api.cofr.io/mcp/fd73c601-5d90-4e3a-99b8-0ea5d5f853e4/icon?v=1790781628585","logo_sha256":"8987b040714d7893caef7320ae4eb5e2d45966dcb78e6eef6b2483cef0ae075f","geometry":{"full_report":"16:9 slides 1920x1080, one PDF page each","mini_report":"one A4 portrait page","discovery_guide":"A4 portrait","discovery_docx":"A4 portrait white page; #000000 or #1A1A1A heading bands, white Montserrat 800 uppercase, 3pt #F06000 rule; Inter #1A1A1A body; orange text #C04A00; editable styles, no page images or text boxes"},"footer":"Prepared with the AI Opportunity Assessment by AI Operator Academy.","fallback_wordmark":"AI OPERATOR ACADEMY","style":"Black full-bleed canvas, print backgrounds. Headings Montserrat 800 uppercase white (weight 800; file default 100). Eyebrows Montserrat 800 uppercase accent. Body Inter cream; labels mono uppercase muted in the system stack ui-monospace, 'SF Mono', Menlo, monospace (not embedded; needs no disclosure). Panels #1A1A1A, 1px rule border. Callouts: #F06000 fill, #000000 text, never white on orange. 72x3px accent rule under titles. Corners 0-4px.","assets":"Verify each SHA-256; embed both fonts in HTML and PDF. Never redraw, recolor or replace the logo. If the logo or a font fails, ask the user to attach it; else return the content in chat or, if the user accepts, use the wordmark in Montserrat 800 uppercase white over a 72x3px #F06000 rule (system-ui if Montserrat fails), disclosed in chat, not as the logo. Never deliver unbranded files silently.","self_inspection":"Inspect every page: Montserrat and Inter embedded or fallback disclosed; no overflow, clipping or overlap; text contrast at least 4.5:1, or 3:1 for large text (at least 24px or 18pt, or bold at least 18.66px or 14pt); footer on every page; claim only files created."}

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds genuinely useful behavior beyond that: the output is 'report content and host rendering,' answered questions are reused, and the embedded spec discloses evidence-grounding rules, a single conditional recommendation, prerequisite validation before a trial, and the fallback of returning the report in chat when file tools are unavailable. The main gap is that these rules are buried in a large static metadata blob rather than stated as invocation behavior, and it is not explained why idempotentHint=false applies (each run re-renders).

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?

The description proper is two front-loaded sentences with no waste: purpose first, output second. Structure is let down only by the surrounding definition, where an extensive host rendering specification is embedded inside the input parameter's description, adding substantial non-parameter noise to the overall definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the rendering rules are documented elsewhere in the definition. What the description itself does not convey is how the interview mode should be driven (how the five questions are asked across turns), what counts as sufficient Mini 1-5 answers to proceed, or how this differs from the full and knowledge-base siblings — meaningful omissions for a multi-mode, report-generating tool.

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?

Single parameter with 100% schema description coverage, so the schema carries the load and 3 is the baseline. The schema description does specify what to send ('only the current assessment request... Mini 1-5 answers in the respondent's words... speaker labels') and what to omit, but roughly ninety percent of that field is static layout and rendering specification unrelated to what the caller should put in 'input,' which dilutes the parameter guidance rather than sharpening it.

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 specific verb and resource ('Run a five-question AI opportunity interview') and states the two operating modes: live interview versus supplied answers producing one evidence-grounded recommendation. The 'mini'/'five-question'/'one recommendation' framing implicitly signals it is the lightweight counterpart to run_aoa_full_assessment, but no sibling is named explicitly, so differentiation still requires the reader to infer from scope.

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?

It implies the two entry conditions (conduct the interview when answers are absent, transform answers when they are supplied) and gives one reuse rule: 'Reuse answered questions.' There is no explicit statement of when to prefer run_aoa_full_assessment or run_aoa_knowledge_base_assessment, and no prerequisites or exclusions are stated outside the embedded host metadata.

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