Skip to main content
Glama
Sign In

LandingBoost

by app.landingboost
OverviewDiscussionsAdmin

Write the missing new wording

write_wording

When get_scan or get_actions shows ai_part.status "failed" (our AI provider was busy or refused the request), write the buyer questions and new wording again from the pages the scan already saved. No new capture and no scan from the limit. Takes about a minute: poll get_scan until ai_part.status is "complete", then call get_actions. Only for a report whose AI part failed: on a report whose AI part is already complete it returns an error ("already complete") and changes nothing.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "scan_id": "<scan_id>"
    },
    "name": "write_wording"
  }
}

Input Schema

NameRequiredDescriptionDefault
scan_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, it discloses the retry-only nature, the approximate one-minute duration, the need to poll, and the exact failure behavior for already-complete reports. It also clarifies that the tool reuses saved pages rather than recapturing, which is important behavioral context for a non-read-only operation.

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?

The description is compact and front-loaded: trigger condition, action, constraints, timing, follow-up workflow, and error behavior all appear in a few tightly packed sentences. There is no filler or repeated information.

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 one-parameter recovery tool with no output schema, it covers the key context an agent needs: eligibility, side effects, timing, polling sequence, and misuse behavior. The remaining gap around scan_id is minor and partially inferable from the sibling tools.

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 0%, so the description should compensate more for the single scan_id parameter. It implies scan_id refers to the scan/report whose AI part failed and references get_scan/get_actions, but it never explicitly defines what scan_id is or where to obtain it.

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 states a specific verb and resource (write the buyer questions and new wording again) and ties it to a precise trigger (ai_part.status is "failed" in get_scan or get_actions). It also distinguishes this from scanning or capturing by explicitly saying no new capture and no scan from the limit.

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?

It clearly says when to use the tool (only when the AI part failed), what to do afterward (poll get_scan until "complete", then call get_actions), and what happens when used incorrectly (on an already complete report it errors and changes nothing). This is explicit when/when-not guidance with named sibling tools.

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

All LandingBoost 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