Skip to main content
Glama

Record shipped work

record_action

Report anything you shipped with the founder: a PR (url = the PR, liveUrl = the page once deployed), a live page, a listing (liveUrl = our page it should link to), an index request, a post the founder published, or a Gmail draft. https URLs only. Free. It is stored as Claimed; call verify to check it (free), and Claimed PRs, pages, listings and posts are re-checked daily for free for 30 days (a listing for 90, weekly after the first 30). Recording the same URL again updates it. Put fix ids in meta.fixIds for site fixes. A PR in a private repo is confirmed merged by record_merges, which grow runs from today's confirm.prs. A listing: record the listing page once it is live; recorded on the directory's submit or account page it waits as submitted, and the listing page recorded later replaces it.

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": {
      "module": "<module>",
      "kind": "<kind>",
      "title": "<title>",
      "url": "<url>"
    },
    "name": "record_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
kindYes
metaNo
titleYes
moduleYes
liveUrlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes well past the annotations (which only declare non-read-only, non-destructive, closed-world) by disclosing the lifecycle state ('stored as Claimed'), free re-verification, the 30-day daily re-check window with the 90-day weekly listing exception, upsert-on-duplicate behavior, and the https-only constraint. These are exactly the operational facts an agent needs before writing.

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?

Front-loads the purpose, which is correct, but the remainder is a single unstructured paragraph mixing URL rules, billing, lifecycle, sibling routing, and listing edge cases. Every sentence carries information, yet the density makes the per-kind rules hard to extract; a short bulleted mapping would serve far better.

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?

For a 6-parameter write tool with no output schema and zero schema descriptions, the definition covers storage state, re-verification cadence, and sibling delegation well. The remaining hole is the 'module' enum (9 values, undocumented anywhere) and the return shape after recording, which matters since nothing else describes it.

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 0%, so the description must carry the load, and it does for the hardest part: url vs liveUrl semantics differ per kind ('url = the PR, liveUrl = the page once deployed', 'liveUrl = our page it should link to') and meta.fixIds is explained. It leaves the 'module' enum entirely undefined and does not map every 'kind' value (STORE_LISTING is never mentioned), so it only partially compensates.

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?

Opens with a specific verb and resource: 'Report anything you shipped with the founder', then enumerates the concrete artifact types (PR, live page, listing, index request, post, Gmail draft) with the URL mapping for each. An agent can distinguish this from record_merges or verify, though the purpose statement is buried in a single dense run-on rather than isolated.

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 explicit when-to-use routing: 'call verify to check it', 'A PR in a private repo is confirmed merged by record_merges', and per-kind timing rules ('record the listing page once it is live'). It also states the dedupe rule ('Recording the same URL again updates it'). It stops short of saying when NOT to use this tool, but the alternative-routing is unusually strong.

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.