Skip to main content
Glama

Generate personalization

spur_generate_personalization
Destructive

Try settings on one property, generate a list preview (up to 10 records), generate all selected list records, or regenerate one saved line. Generation can spend Actions even in preview mode. Requires approval. Never sends outreach; review/edit/approve the stored lines separately.

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say the call is destructive, non-idempotent, and open-world. The description adds genuinely non-obvious behavior on top: generation consumes Actions even in preview mode, an explicit user approval is required, and the tool never sends outreach, leaving the generated lines stored for separate review. Those are exactly the cost and side-effect facts an agent needs before invoking a destructive operation.

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?

Two sentences, front-loaded with the operation list, then the cost/approval/no-send constraints. The first sentence is a long run-on chain of four clauses but every clause carries distinct routing information, so nothing is wasted; only the formatting could be tighter.

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 destructive, credit-spending multi-branch mutation with no output schema, the description covers what will be spent, that approval is mandatory, that delivery does not happen here, and where the output lands for review. Nothing essential to calling it correctly is missing.

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 already 100%, so the baseline is 3. The description still adds discriminative meaning across the oneOf branches (which action corresponds to which mode) and a semantic detail not visible from the schema alone, namely that preview returns at most 10 records. It does not clarify the confirm/force defaults beyond what the schema states.

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 names the resource (personalization) and enumerates the four concrete operations the single tool performs: try settings on one property, list preview capped at 10 records, generate all selected list records, and regenerate one saved line. That maps directly to the three oneOf action branches, so an agent can tell what 'generate' means here versus the read/review siblings.

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?

It gives clear usage context per mode (try = one property, list preview vs all, regenerate = one saved line) and closes with a routing rule: 'review/edit/approve the stored lines separately', which points the agent at the review family instead of this tool. It stops short of naming the specific sibling tools, so the routing is directional rather than explicit.

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