Skip to main content
Glama

Klarix Intelligence Engine

Tech stack teardown (confirmed vs inferred + displacement angles)

teardown_tech_stack
Read-only

Deconstruct an account's technical infrastructure, dev tools, cloud providers, AI/data stack, and identify displacement vulnerabilities.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
client_idNoKlarix client id (kebab-case, e.g. "alium-batteries"). Loads company name, domain, value propositions, win themes, and ICP from clients/{client_id}/context.json when that file is reachable. Explicit arguments always override it.
our_domainNoYour own web domain, e.g. "klarix.ai". Lets the tool research your side of the comparison.
focus_areasNoLayers to probe. Defaults to all five: frontend_backend, cloud_infra, data_ai, business_tools, security.
target_domainYesDomain of the account whose stack you want deconstructed, e.g. "acme.com".
target_verticalNoThe market this account operates in, e.g. "medical device OEMs". Sharpens which stack gaps matter.
our_company_nameNoYour company name. Curates the analysis toward how YOU win instead of a generic read.
our_differentiatorsNoWhat you actually win on, in your words, e.g. ["3-7 day delivery", "done-for-you, not DIY"]. Anchors talk tracks to claims you can defend.
target_company_nameNoProper name of the account, when the domain does not make it obvious.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
sourcesYes
unknownsYes
cloud_infraYes
focus_areasYes
our_contextNo
stack_summaryYes
target_domainYes
target_verticalYes
business_toolingYes
confidence_detailNo
data_and_ai_stackYes
evidence_confidenceYes
target_company_nameYes
application_and_backendYes
displacement_opportunitiesYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description is not responsible for safety disclosure. The description adds only outcome-level context (displacement vulnerabilities) and the title hints at a confidence distinction (confirmed vs inferred), but it does not explain confidence levels, data-freshness, or that results may be based on live research. No contradiction with annotations.

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?

One tightly worded sentence delivers the verb, resource list, and intended analytical outcome; the key scope ('account's technical infrastructure') is front-loaded. No filler, redundant clauses, or irrelevant caveats. The title adds the confidence/displacement framing without bloating the description.

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?

The rich input schema (8 documented params), output schema, and read-only/open-world annotations cover most operational facts an agent needs. The main gap is placement: no indication of when to choose this over adjacent tools like generate_displacement_playbook or teardown_product_spec. That keeps it at a solid but not fully complete level for a tool of this complexity.

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%, with each of the 8 parameters having descriptive text (e.g., target_domain, focus_areas, our_differentiators). The tool description itself adds no parameter-level meaning, so it appropriately stays at the baseline. Nothing is missing because the schema already carries the burden.

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?

The description uses a specific verb ('Deconstruct') with a precise resource list ('technical infrastructure, dev tools, cloud providers, AI/data stack') and a named outcome ('identify displacement vulnerabilities'). This clearly marks the tool as a stack-analysis action rather than a product-spec or playbook tool. The title's 'confirmed vs inferred + displacement angles' reinforces the distinctive 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?

There is no explicit when-to-use or when-not-to-use guidance and no named alternatives, despite 14 siblings such as generate_displacement_playbook or get_deep_research. It is inferable from the title and resource that this is for tech-stack teardown, which is enough for a minimum-viable score. But the description leaves the agent to infer how it relates to adjacent research and playbook tools.

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.

TDQS

A4/5.0
Disambiguation3/5

Most tools have clearly different output formats (one-pager vs. exhaustive probe vs. battlecard vs. SWOT matrix), but several overlap in the company/competitor research space. get_company_intelligence vs. get_deep_research and analyze_head_to_head vs. get_competitor_battlecard vs. generate_swot_analysis could cause misselection without careful reading.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern with action-first verbs (analyze_, detect_, find_, generate_, get_, score_, search_, teardown_). The verb choices map meaningfully to the tool's function, and there is no mixing of naming conventions.

Tool Count5/5

15 tools is at the upper end of the ideal range but appropriate for a broad B2B intelligence engine covering prospecting, research, competitive analysis, teardowns, and outreach. Each tool represents a distinct functional deliverable, so the count feels justified rather than padded.

Completeness5/5

The toolset covers the full intelligence workflow: prospect discovery, fit scoring, company and competitor research, buying committee mapping, market landscape analysis, technical teardowns, and outreach generation. There are no obvious dead ends for the stated purpose of competitive displacement and sales intelligence.

Resources