Skip to main content
Glama

Lists AI answers read

outreach_targets

The "best X" and "X alternatives" pages AI engines cite when buyers ask, on other sites and without this product on them, most cited first: for each, the buyer questions it is cited for, the author from the page's own byline, and their work email when one is found and verified. A page with no verified email says why; use the site's contact page in the browser then. Pages already written to (record_action with meta.type "outreach") or skipped never come back. Costs $0.60 from the balance, charged only when it returns. for a batch with new pages to look up, and nothing when they all list this product already; pages looked up before come back free, and a call with skip only records the skips and looks nothing up, free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "outreach_targets"
  }
}

Input Schema

NameRequiredDescriptionDefault
skipNoPage URLs the founder will not ask: a vendor's own list of its rivals, a dead blog. Never offered again.
countNoPages in this batch. Default 5

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, openWorldHint=true, destructiveHint=false; the description goes well beyond them with a concrete price ($0.60 from the balance), a charge-on-success rule, free conditions (already-listed pages, previously looked-up pages, skip-only calls), and the irreversible exclusion that written-to or skipped pages 'never come back'. Those are exactly the non-obvious traits an agent needs before spending money or burning a target.

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

Conciseness2/5

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

The content is valuable but the prose is a run-on with broken syntax — 'charged only when it returns. for a batch with new pages to look up,' is a sentence fragment starting with a lowercase word, and the final clause chains four cost rules with semicolons. Nothing is front-loaded as a verb-first summary, so the agent must parse the whole block to extract the action.

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 only two parameters, no output schema, and open-world lookups, the description carries the burden of explaining returns (buyer questions, byline author, verified work email, and the reason when no email is found) plus the fallback to the contact page, and it does. The remaining gap is that it never says what a page entry looks like structurally or how many results come back per count.

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, and the description earns the extra point by explaining skip behavior beyond the schema's 'Never offered again': a call with skip only records skips, looks nothing up, and is free. Count's default of 5 and the batch concept are already in the schema, so nothing further is added there.

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?

The description names a specific resource: "'best X' and 'X alternatives' pages AI engines cite when buyers ask, on other sites and without this product on them," which is far more precise than the odd title 'Lists AI answers read'. It never leads with a verb (the opening is a noun phrase), so the action is inferred rather than stated, but an agent can still tell this apart from record_action or the other *_targets tools by the resource described.

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

Usage Guidelines3/5

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

Usage is implied through cost conditions ('for a batch with new pages to look up... nothing when they all list this product already') and through the skip-only mode, and record_action is named as the downstream consumer. However, there is no explicit 'use this when / do not use this when' framing, and among the many sibling *_targets tools (followup_targets, launch_targets, listing_targets, outbound_targets) nothing here distinguishes which one applies.

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