Mark

Draft Competitor Page

draft_competitor_page

Idempotent

Drafts a comparison page for one tracked competitor as a competitor_page draft post: kind vs (" vs ", which also answers " alternative" searches) or pricing (" pricing", what they charge and how you compare). There is no alternative kind: kind alternative is refused, so draft the vs page. One AI model call writes it from Mark's facts about them (price claims sourced on their own site, this week's AI answers that named them and not you, their ranked keywords). Each fact gets a numbered marker, and Mark adds a Sources section with each source and its checked date. A fact Mark has no source for is a [confirm: …] placeholder; every price is one when no price claim is sourced on their site (add one with add_source and save_claim). No tables. When that competitor already has a live (not archived) post of that kind, returns it and writes nothing; markAppUrl opens the editor, or the review page once it is past draft. Refuses an unknown or untracked competitor, and one whose name or domain matches a content exclusion. A blocked phrase in the generated text saves nothing. Never submits: open placeholders, tables and numbers no active claim states fail the content checks, so fix them, then call submit_post. Takes up to a minute. Related: list_competitors, get_competitor_scorecard, check_draft, save_post, submit_post.

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": {
      "competitorId": "<competitorId>",
      "kind": "<kind>"
    },
    "name": "draft_competitor_page"
  }
}

Input Schema

Name	Required	Description	Default
`kind`	Yes	vs or pricing.
`competitorId`	Yes	Competitor id from list_competitors.

Output Schema

Name	Required	Description	Default
`postId`	Yes
`status`	Yes
`created`	Yes
`markAppUrl`	Yes
`openPlaceholders`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 23, 2026

changedInput schema / properties / kind / description

Previous value: -"vs, alternative or pricing."New value: +"vs or pricing."

changedInput schema / properties / kind / enum

Previous value: -[
-  "vs",
-  "alternative",
-  "pricing"
-]New value: +[
+  "vs",
+  "pricing"
+]

AddedOct 20, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond annotations: idempotency is explained concretely (an existing live post is returned and nothing is written), and it discloses refusal cases, silent-failure cases (blocked phrase saves nothing), placeholder/source-marker behavior, latency ('up to a minute'), and that it never submits. No contradiction with readOnlyHint=false or destructiveHint=false.

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?

Purpose and kind definitions are front-loaded, and nearly every sentence carries unique information. It is dense and slightly overstuffed — the refusal, idempotency, sourcing, and validation rules run together in long compound sentences that would scan better as bullets — but there is little true filler.

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?

For a generating, non-submitting mutation with two params and an output schema, the description covers everything an agent needs: inputs' meaning, refusal conditions, what gets written, what blocks success, and the next step. Return-value detail is unnecessary given the output schema but not harmful.

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 is 3, but the description earns more by explaining what 'vs' semantically covers (also answers '<them> alternative' searches) and that 'alternative' is rejected despite not appearing in the enum. competitorId's provenance is already in the schema.

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?

Opens with a specific verb+resource ('Drafts a comparison page for one tracked competitor as a competitor_page draft post') and then defines both kinds by the search intent each targets. The output artifact (a draft post) is named, so an agent knows exactly what it produces versus sibling tools like save_post or check_draft.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Explicitly rules out the 'alternative' kind and directs the agent to draft the vs page instead, states the prerequisite facts Mark draws from, and routes to add_source/save_claim for missing prices and submit_post after fixing failures. When-not conditions (unknown competitor, untracked, excluded, already-live post) are all enumerated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Mark tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?