Skip to main content
Glama

SignalPipe

by io.github.AbYousef739
OverviewDiscussionsAdmin

suggest_anchors

Read-only

Generate candidate anchor sentences for a product. CALL THIS BEFORE add_product.

Anchors are the single highest-leverage field in the whole system — they
are what every incoming post is compared against, so they decide what the
user does and doesn't get shown. Writing them well is hard and most people
write marketing copy by mistake, so use this and then let the user edit.

Recommended setup flow:
  1. Ask the user three things: what the product is, who buys it, and what
     it does for them.
  2. Call this tool.
  3. SHOW the returned anchors to the user and invite edits — they know
     their buyers' words better than any model does.
  4. Call `add_product` with the approved list, then `reload_products`.

A good anchor is the BUYER speaking about their PROBLEM, moments before
they'd want this product ("my stream background is just a static image and
looks boring", "we're paying for seats nobody uses"). A bad anchor is the
seller describing the product ("premium audio-reactive visual engine").
Product-voice anchors match other sellers; buyer-voice anchors match buyers.

Returns: {"anchors": [str, ...]}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesThe product's name.
countNoHow many anchors to suggest, 3 to 15 (default 8).
value_propYesWhat the product does for its buyer, in a sentence.
descriptionNoOptional. A longer description of the product.
target_audienceNoOptional. Who buys it: one buyer, described narrowly.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / count / description
      Added value: +"How many anchors to suggest, 3 to 15 (default 8)."
    • addedInput schema / properties / description / description
      Added value: +"Optional. A longer description of the product."
    • addedInput schema / properties / name / description
      Added value: +"The product's name."
    • addedInput schema / properties / target_audience / description
      Added value: +"Optional. Who buys it: one buyer, described narrowly."
    • addedInput schema / properties / value_prop / description
      Added value: +"What the product does for its buyer, in a sentence."
  2. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered before the description is read. The description adds real behavioral context beyond that: the return shape {"anchors": [str, ...]}, the fact that anchors drive what posts users see, and the instruction to route output through human editing rather than trusting it directly.

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

Conciseness5/5

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

Front-loaded with the imperative action and the sibling-ordering constraint, then a numbered flow, then a criteria contrast. The length is justified by the tool's high-stakes workflow role and every paragraph carries distinct information; nothing is 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?

No output schema exists, but the description supplies the return shape itself ({"anchors": [str, ...]}) plus the surrounding workflow, so an agent has everything needed to call it and act on the result. Annotations cover the safety profile and the description covers the semantic and procedural gaps.

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 description coverage is 100%, so the baseline is 3 and the schema already documents all five parameters. The description adds meaning by mapping the pre-call questions (what the product is, who buys it, what it does) onto name/value_prop/target_audience, and by illustrating what value_prop content should look like via buyer-voice vs product-voice examples.

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?

States a specific verb and resource ("Generate candidate anchor sentences for a product") and immediately positions it against a sibling with "CALL THIS BEFORE `add_product`". An agent can distinguish it from add_product without opening either schema.

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?

Provides an explicit recommended setup flow (ask three questions, call this tool, show anchors for edits, then add_product, then reload_products), which is direct when-to-use and ordering guidance naming the relevant alternatives. It also gives an explicit 'when it's easy to get wrong' rationale.

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

All SignalPipe 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