Skip to main content
Glama

Run a peer study

research_run

Find up to 8 products a step ahead of this one (the same job, the same buyers, sold the same way), read what each shows in public today and how it started, read this site the same way, and find what it can learn from them, each with evidence, a first step and the move it becomes. In the background, a few minutes; call research afterwards. Needs a finished AI visibility check; for an iOS app, its App Store search check instead (the week's listing set), and the apps studied are the ones that top those searches, read on the App Store. Costs $1.30 from the balance, charged only when it returns. Not charged when fewer than 2 such products can be read. At most one a day. State the price and wait for a yes before every study. domains: products the founder has in mind, by domain or URL (an app by its App Store link); they are studied first in this study and every one after it (at most 5 kept, the newest last).

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": "research_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainsNoProducts the founder named when asked which ones they have in mind, by domain or URL; for an app, App Store links. Leave out when they named none.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / domains / description
      Previous value: -"Products the founder named when asked which ones they have in mind, by domain or URL. Leave out when they named none."New value: +"Products the founder named when asked which ones they have in mind, by domain or URL; for an app, App Store links. Leave out when they named none."
  2. Changed2 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / domains
      Added value: +{
      +  "description": "Products the founder named when asked which ones they have in mind, by domain or URL. Leave out when they named none.",
      +  "items": {
      +    "maxLength": 300,
      +    "minLength": 3,
      +    "type": "string"
      +  },
      +  "maxItems": 5,
      +  "type": "array"
      +}
  3. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare that this is a non-read-only, open-world, non-destructive call. The description adds what actually matters: it runs in the background for a few minutes, costs $1.30 from the balance, is charged only when it returns, is free when fewer than 2 qualifying products can be read, and is capped at one per day. The consent requirement is behavior the schema cannot express at all.

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

Conciseness3/5

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

Almost every sentence carries load, but the text is one dense run-on block mixing purpose, prerequisites, pricing, rate limits, and parameter retention. The critical consent requirement and the price are buried mid-paragraph rather than front-loaded, which makes skimming for the go/no-go conditions harder than it should be.

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 an asynchronous, paid, once-per-day job with no output schema, the definition covers everything an agent needs before calling: prerequisites, latency, billing rules with the refund edge case, the required human confirmation, and the tool to call afterwards for results. The absence of a return schema is compensated by naming the follow-up tool.

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 the single domains parameter is already documented as domain/URL or App Store link with a leave-out case, so the baseline is 3. The description does add real meaning beyond the schema: these domains are studied first in this run and in every later run, with at most 5 retained and the newest kept last. That persistence detail is useful but not elaborated enough to lift the score further.

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 concrete verb and resource: find up to 8 products a step ahead (same job, same buyers, same selling motion), read their public surface and history, read this site the same way, and produce evidence plus a first step per lesson. That is far more specific than the title 'Run a peer study'. It does not clearly differentiate itself from the sibling research tool, which it only mentions as the polling step afterwards, so an agent must infer that boundary.

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?

Preconditions are explicit: a finished AI visibility check is required, or for an iOS app the App Store search check over the week's listing set. It also states the rate limit (at most one a day), the follow-up call ('call research afterwards'), and a required consent gate (state the price and wait for a yes before every study). This leaves little to inference about when and how to invoke it.

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