Skip to main content
Glama
Sign In

seodraft

by app.seodraft
OverviewDiscussionsAdmin

Approve post

approve_post
Destructive

Approve one article in one call: the human's act, or the agent's when the workspace approvalMode (see pipeline_status) is agent. It refuses unless the last run_gate check passed (degraded reason gate-failed, and nothing changes), then moves the article to ready and, when this workspace has a delivery destination and a token saved, delivers it in the same act. That is the whole approval: there is no separate deliver step to remember, and nothing here publishes: publishing is a human click in the seodraft app. The result carries approvalMode. delivered is the receipt or null when nothing is configured to deliver to. For a git destination (provider github) it carries label, repo, branch, path, previousPath, commitUrl, htmlUrl, updated and pendingImageSlots. For Sanity (provider sanity) the draft drafts.seodraft-<id> is created or patched, never published and never deleted, and re-delivering patches only the fields seodraft maps; the receipt carries label, projectId, dataset, documentId, studioUrl, updated, pendingImageSlots and degradations (what the destination's Portable Text could not carry, which the human fixes in Studio). If the destination refuses the write the article stays ready (the approval was valid) and degraded reason delivery-failed carries the CMS's own reason in deliveryReason; re-approving retries the delivery and overwrites the same draft. deliveryReason published means the article is live from the seodraft app on a git destination and a draft file would take it offline, so nothing was written. With approvalMode human it records an approval the user gave explicitly.

Input Schema

NameRequiredDescriptionDefault
idYes
workspaceIdNoThe workspace this call acts on, as listed by list_workspaces. Left out, the call uses the workspace the account is in right now.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / workspaceId
      Added value: +{
+  "description": "The workspace this call acts on, as listed by list_workspaces. Left out, the call uses the workspace the account is in right now.",
+  "type": "string"
+}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say destructive/open-world/non-idempotent; the description far exceeds them by disclosing the gate-check refusal path, degraded reasons (gate-failed, delivery-failed, deliveryReason `published`), that a Sanity draft is created/patched but never published or deleted, that re-approving overwrites the same draft, and that a failed delivery leaves the article ready.

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?

Front-loaded with the action and its gate precondition, and every segment carries real information. However, the receipt enumeration and Sanity details run together in long compound sentences with heavy parentheticals, making it denser than necessary for a two-parameter tool.

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?

With no output schema and only two parameters, the description compensates by enumerating the exact receipt fields per provider (github: label, repo, branch, path, previousPath, commitUrl, htmlUrl; sanity: projectId, dataset, documentId, studioUrl, degradations) and how failures are surfaced. An agent has everything needed to call and interpret the result.

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 50%: workspaceId is documented in the schema itself and the description doesn't add to it, while `id` is only implied by 'one article' with no format or source (e.g., get_post/list_posts) given. The description is rich overall but adds little parameter-level meaning beyond the schema.

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?

Opens with a specific verb+resource+scope ('Approve one article in one call') and immediately distinguishes the tool from the sibling deliver_draft by stating there is no separate deliver step. It also draws the boundary against publishing ('nothing here publishes: publishing is a human click in the seodraft app').

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?

Gives explicit preconditions ('refuses unless the last run_gate check passed'), names the gating condition for the two modes (approvalMode agent vs human, referencing pipeline_status), and states when to use it rather than a re-approval or an external publishing action. Alternatives and exclusions are both covered.

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

All seodraft 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