Skip to main content
Glama

Persuasion Taxonomy

Explain why marketing is not converting

explain_why_not_converting
Read-onlyIdempotent

Work out why an ad, a landing page, an email or a whole funnel isn't converting, starting from what you can see. Maybe people don't click (a low CTR), or they click and bounce, or they read and don't buy. Maybe they abandon the checkout or the form, the leads never buy, customers buy once and leave, or emails don't get opened or get opened and nobody clicks. Whatever the symptom, you get back the reader questions most likely going unanswered, what to check in the copy first, and the problems copy can't fix, which are worth ruling out, along with techniques to try and the test that would confirm the diagnosis. It answers questions like why marketing "isn't working", "isn't converting" or "isn't selling", or why results dropped.

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": {
      "symptom": "<symptom>"
    },
    "name": "explain_why_not_converting"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoThe kind of copy it is: ad, landing_page, sales_letter for long-form sales copy, email, email_subject, social_post, video_script or headline.
detailsNoAnything you know: the numbers, what changed recently, the offer and the audience.
symptomYesWhat you can see happening. Use low_click_through when people see it and don't click, high_bounce when they click and leave fast, reads_but_no_action when they read and don't convert, starts_but_abandons when they abandon the checkout or form, leads_dont_buy when signups never buy, buys_once_no_return for refunds, churn and no repeat orders, low_open_rate when emails don't get opened, and opens_no_clicks when they get opened but not clicked.
categoryNoThe industry, for a comparison with what brands in that category usually do. There is enough data for apparel, automotive, b2b_saas, beauty_skincare, business_coaching, consumer_tech, dtc_food_bev, dtc_health, fitness_health, home_goods, info_product, investing, marketing_education, otc_pharma, personal_care, personal_development, supplements, weight_loss. Any other category still works, just without the comparison.
persuasion_modeNoHow hard the copy is allowed to push. Balanced is the default, persuasive and sustainable over time. Equity protects long-term trust, so it rules out fear, hype and hard-sell moves. Aggressive is for short-term direct response and allows fear, threat and hard scarcity. In every mode, the claims stay true.balanced

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / category / description
      Previous value: -"The industry, if you want to compare against what brands in that category usually do. There is enough data for apparel, automotive, b2b_saas, beauty_skincare, business_coaching, consumer_tech, dtc_food_bev, dtc_health, fitness_health, home_goods, info_product, investing, marketing_education, otc_pharma, personal_care, personal_development, supplements, weight_loss. Any other category still works, just without the comparison."New value: +"The industry, for a comparison with what brands in that category usually do. There is enough data for apparel, automotive, b2b_saas, beauty_skincare, business_coaching, consumer_tech, dtc_food_bev, dtc_health, fitness_health, home_goods, info_product, investing, marketing_education, otc_pharma, personal_care, personal_development, supplements, weight_loss. Any other category still works, just without the comparison."
  2. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value by stating what comes back: unanswered reader questions, what to check in the copy first, problems copy can't fix, techniques to try, and the confirming test. That output disclosure is genuinely useful given there is no output schema, but it stops short of describing depth, limits, or what happens when symptom and format disagree.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is well front-loaded and states purpose and input type immediately. The long middle passage ('Maybe people don't click... or they click and bounce...') is a near-verbatim restatement of the eight symptom enum values already documented in the schema, which is significant waste, and the trailing 'questions like' sentence overlaps with it again.

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?

For a five-parameter, no-output-schema tool, the definition covers input intent, the symptom taxonomy semantics, and the shape of the returned diagnosis, which is what an agent most needs. The main omissions are sibling differentiation and any note on whether optional parameters like category or persuasion_mode materially change the diagnosis.

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 coverage is 100%, with enum descriptions that already spell out each symptom and persuasion mode, so the schema does the heavy lifting and a 3 baseline applies. The description adds only the framing 'starting from what you can see', which implies symptom should be an observed metric, but says nothing about the other four parameters.

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 gives a concrete verb-and-resource ('work out why an ad, a landing page, an email or a whole funnel isn't converting') and enumerates the observable symptoms it handles, so the purpose is unambiguous. It never distinguishes itself from the close sibling 'diagnose_marketing_copy', leaving the agent to guess which diagnosis tool applies.

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 context is clear: trigger it when marketing 'isn't working', 'isn't converting', or results dropped, starting from an observable symptom. However, there are no exclusions and no routing to alternatives such as diagnose_marketing_copy, plan_marketing_copy or check_headlines, so the agent gets implied rather than explicit guidance on when this is the right choice.

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.