Skip to main content
Glama
Sign In

Siren

by ai.mysiren
OverviewDiscussionsAdmin

plan_ads

Siren drafts an ad plan from one prompt: goal, audience, budget inside the caps, platforms and the ads to make (shape, hook, headline, text). Nothing is made or spent. Show the human the plan, then make_ads. With test, the versions split one budget and the verdict rule is set before any spend.

Input Schema

NameRequiredDescriptionDefault
testNoMake the plan a split test: "hook" tests openings, "words" tests the text. Omit for a normal plan.
promptYesThe goal in plain words, e.g. "more Pro signups from US founders, $20 a day for two weeks".
variantsNoVersions in a test, 2 or 3.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / test
      Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "hook",
+        "words"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Make the plan a split test: \"hook\" tests openings, \"words\" tests the text. Omit for a normal plan."
+}
    • addedInput schema / properties / variants
      Added value: +{
+  "default": 3,
+  "description": "Versions in a test, 2 or 3.",
+  "type": "integer"
+}
  2. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and idempotentHint=false, and the description closes the obvious ambiguity by stating 'Nothing is made or spent' and that the verdict rule is fixed 'before any spend' — real behavioral context beyond the hints. It still doesn't say whether the plan persists or what re-invoking it does (relevant given idempotentHint=false), and 'budget inside the caps' only implicitly points at the cap-checking sibling.

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?

Four short sentences, front-loaded with what is produced before the guardrail and the handoff. The final test sentence is slightly compressed/telegraphic ('the verdict rule is set'), but no sentence is filler.

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?

With an output schema covering the returned plan and annotations covering safety flags, the description supplies the missing pieces: no spend/no creation, human review before make_ads, and split-test semantics. What's absent is where the plan lives afterward and how it relates to clarify_brief, which matters in a 60+ sibling catalog.

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% and all three parameters are documented in-schema, so baseline is 3. The description adds a little meaning: 'from one prompt' signals the prompt drives the whole plan, and the test clause notes that versions share one budget and get a pre-committed verdict rule — but it doesn't clarify the 'hook' vs 'words' distinction or the 2-or-3 variants limit beyond what the schema already says.

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?

Specific verb+resource: 'Siren drafts an ad plan from one prompt', with the plan's contents enumerated (goal, audience, budget, platforms, ad shapes/hooks/headlines/text). It explicitly distinguishes itself from the sibling that produces the actual ads ('then make_ads'), so an agent can tell the two apart without opening a schema.

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?

Gives a clear workflow rule: 'Show the human the plan, then make_ads', plus the conditional 'With test...' instructing when to use split-test mode. It does not differentiate against other adjacent siblings such as clarify_brief, create_campaign, or ad_autopilot, so the routing guidance is clear but not exhaustive.

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

All Siren toolsInspect
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