Skip to main content
Glama

Check an API build

writ_discovery_status
Read-onlyIdempotent

Status of a website-to-API build (a guided one, or one started in the Writ app). wait=true is one held call (up to 75 s) that follows the build to its newest rung and returns when it is done or parked. Answers: succeeded (workflow_id, functions, run_example), failed, cancelled, or needs_guidance (the build is the caller's to finish with writ_website_to_api build_id=; its map comes with 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": {
      "build_id": "<build_id>"
    },
    "name": "writ_discovery_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitNoOne held call until done or parked.
build_idYes
timeout_secondsNoCeiling for wait=true (up to 75).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / properties / build_id / description
      Removed value: -"The build id from writ_website_to_api."
    • changedInput schema / properties / timeout_seconds / description
      Previous value: -"Ceiling for wait=true (≤75)."New value: +"Ceiling for wait=true (up to 75)."
    • changedInput schema / properties / wait / description
      Previous value: -"One held call (≤75s) that follows escalations to the newest rung and returns when that build is terminal or parked as needs_guidance. Still building at the ceiling, it answers with the build_id to repeat it with."New value: +"One held call until done or parked."
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare this as a read-only, idempotent, non-destructive check, so the safety profile is covered. The description adds beyond that: the held-call semantics and 75 s ceiling, the four terminal states, and the fields returned on success (workflow_id, functions, run_example). It does not say what happens if the 75 s ceiling is hit, which is the one meaningful behavioral gap.

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

Conciseness4/5

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

The purpose is front-loaded in the first clause, and the sentence is dense but every part (build types, wait semantics, terminal states, handoff) carries information. It reads as one long run-on sentence with stacked parentheses, which costs a little clarity, but nothing is filler.

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 no output schema, the description does the work of explaining return values: succeeded with workflow_id/functions/run_example, failed, cancelled, and needs_guidance with the map. Combined with annotation coverage of safety, an agent has enough to call it and interpret the response. The only shortfall is ambiguity about what a timeout on wait=true returns.

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?

The schema documents wait and timeout_seconds but leaves build_id bare; the description compensates by showing build_id in the handoff call and implying it identifies the build to check. It also enriches wait=true beyond the schema's terse 'One held call until done or parked' by explaining that it follows the build to its newest rung and returns when done or parked. Not every parameter is fully explained, but meaningful semantics are added.

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 opens with a specific verb and resource: 'Status of a website-to-API build', and scopes the build types it covers (guided, or started in the Writ app). It also names the related sibling writ_website_to_api for the needs_guidance case, so an agent can tell this apart from the build-creating tool.

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?

It explains the two operating modes: without wait it is presumably a status check, and with wait=true it is 'one held call (up to 75 s)' that follows the build to its newest rung. It also routes the needs_guidance state to writ_website_to_api with build_id. What is missing is explicit guidance on repeated polling (how often to call when wait=false) — the when-to-use is clear but not fully exhaustive.

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.