Skip to main content
Glama

Build the audience strategy

seed_marketing_strategy
Destructive

Have our AI build the site's audience strategy from what the site says about the business: personas, buying stages, pain points and competitors. If a strategy already exists it is returned unchanged — unless force is true, which REBUILDS it and clears every messaging brief written for its cells (say so before asking the user to approve). Counts toward the hourly AI limit.

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": {
      "site_id": "<site_id>"
    },
    "name": "seed_marketing_strategy"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNoRebuild an existing strategy, discarding its cell briefs
site_idYesThe site, from list_sites
user_goalNoOptional: the user's goal behind this call, in one short sentence of plain words (e.g. "add a page so customers can book tables"). No names, emails or other personal details.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / user_goal
      Added value: +{
      +  "description": "Optional: the user's goal behind this call, in one short sentence of plain words (e.g. \"add a page so customers can book tables\"). No names, emails or other personal details.",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.1/5.0
Behavior5/5

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

With destructiveHint=true already declared, the description goes further and specifies exactly what is destroyed — every messaging brief written for the strategy's cells — and mandates warning the user before approval. It also discloses the AI-quota rate limit and the idempotent-return behavior, both of which are absent from annotations.

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?

Three sentences, front-loaded with what gets built, then the idempotency/force rule, then the quota note. The parenthetical about telling the user is well-placed but makes the middle sentence dense enough to read twice.

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?

No output schema exists, and the description covers the meaningful return cases (fresh strategy vs. unchanged existing one), the destructive side effect, and the quota cost — enough for an agent to call and report correctly. It omits how long generation takes or what the strategy looks like beyond the listed components.

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%, so all three parameters are documented in the schema, making 3 the baseline. The description reinforces force's destructive consequence but adds nothing for site_id or the optional user_goal, which the schema already explains adequately.

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?

States a specific verb and resource ('build the site's audience strategy') and enumerates the outputs (personas, buying stages, pain points, competitors), so the agent knows exactly what the call produces. The implicit contrast with get_marketing_strategy (existing strategy returned unchanged) helps, but no sibling is named outright, so differentiation is inferred rather than stated.

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?

Explains the no-op path (existing strategy returned unchanged) and the exact condition that overrides it (force=true rebuild), plus the operational constraint of the hourly AI limit and the instruction to disclose destruction before user approval. It stops short of naming the read-side alternative (get_marketing_strategy) or saying when *not* to seed at all.

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