Skip to main content
Glama

List the Failed tab

list_failed
Read-onlyIdempotent

[read-only] The Schedule → Failed backlog of the brand: one row per platform of a post that did not go out, with its row id, postId, contentId, account, slot, lastError, reasonClass and coverage ("live" / "rebooked" when the platform is now covered elsewhere, null when nothing known covers it). Filters: state (open = what the tab shows, the default), platform, zernioAccountId, reasonClass, slotAfter / slotBefore. Follow cursor until it is null; a page can be short. Full description and schema: describe_tool {"name":"list_failed"}. (Wraps GET /api/v2/failed.)

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": "list_failed"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoInteger, e.g. 20. Items per page (1-50, default 20).
stateNoFormat: string; e.g. "open". Processing state to select.open
cursorNoOpaque string, e.g. "eyJvIjoyMH0". The `nextCursor` of the previous page. Omit for the first page.
fieldsNoString array, e.g. ["id", "title"]. Top-level item fields to return instead of the summary. Default: a summary of each item's plain fields.
brandIdNoFormat: string; e.g. "brandId_123". Brand identifier from list_brands; use a real ID.
platformNoFormat: string; e.g. "instagram". Social platform identifier.
slotAfterNoFormat: ISO 8601 with timezone; e.g. "2026-11-20T12:00:00-06:00".
slotBeforeNoFormat: ISO 8601 with timezone; e.g. "2026-11-20T12:00:00-06:00". Only rows whose slot is before this instant.
reasonClassNoFormat: string; e.g. "auth_or_account". Failure category to filter.
zernioAccountIdNoFormat: string; e.g. "zernioAccountId_123". Zernio connected account identifier.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • addedInput schema / properties / brandId / description
      Added value: +"Format: string; e.g. \"brandId_123\". Brand identifier from list_brands; use a real ID."
    • changedInput schema / properties / cursor / description
      Previous value: -"The `nextCursor` of the previous page. Omit for the first page."New value: +"Opaque string, e.g. \"eyJvIjoyMH0\". The `nextCursor` of the previous page. Omit for the first page."
    • changedInput schema / properties / fields / description
      Previous value: -"Top-level item fields to return instead of the summary. Default: a summary of each item's plain fields. For one item in full, use the matching get_ tool."New value: +"String array, e.g. [\"id\", \"title\"]. Top-level item fields to return instead of the summary. Default: a summary of each item's plain fields."
    • changedInput schema / properties / limit / description
      Previous value: -"Items per page (1-50, default 20)."New value: +"Integer, e.g. 20. Items per page (1-50, default 20)."
    • addedInput schema / properties / platform / description
      Added value: +"Format: string; e.g. \"instagram\". Social platform identifier."
    • addedInput schema / properties / reasonClass / description
      Added value: +"Format: string; e.g. \"auth_or_account\". Failure category to filter."
    • changedInput schema / properties / slotAfter / description
      Previous value: -"Only rows whose slot is at or after this instant (ISO 8601 with an offset)."New value: +"Format: ISO 8601 with timezone; e.g. \"2026-11-20T12:00:00-06:00\"."
    • changedInput schema / properties / slotBefore / description
      Previous value: -"Only rows whose slot is before this instant."New value: +"Format: ISO 8601 with timezone; e.g. \"2026-11-20T12:00:00-06:00\". Only rows whose slot is before this instant."
    • addedInput schema / properties / state / description
      Added value: +"Format: string; e.g. \"open\". Processing state to select."
    • addedInput schema / properties / zernioAccountId / description
      Added value: +"Format: string; e.g. \"zernioAccountId_123\". Zernio connected account identifier."
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is covered; the description still adds real behavior: unstable page sizes ('a page can be short') and the cursor-termination rule. The definition of the `coverage` values ('live' / 'rebooked' / null meaning nothing known covers it) is context an agent could not get from annotations. It does not discuss rate limits or ordering, keeping it short of a 5.

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?

Dense but front-loaded: the resource and row shape come first, filters next, pagination last, and the describe_tool pointer closes it. The parenthetical '(Wraps GET /api/v2/failed.)' is a small bonus for tracing behavior. Some clauses are packed tightly into one paragraph, which costs a little readability.

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 10-parameter, all-optional list tool with no output schema, the description covers the row shape, the meaning of the non-obvious coverage field, the filter set, the default state, and pagination termination. An agent can call it correctly and interpret the response without further lookups.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks: state=open is the default that corresponds to what the tab shows, and the slot range is described as a filter pair alongside reasonClass and platform. It groups the filters into a single readable set, though it does not explain the non-open state values (pending, retrying, dismissed, resolved) beyond what the enum implies.

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?

States a specific resource and scope: the Schedule → Failed backlog of a brand, one row per platform of a post that did not go out. It enumerates the returned row fields (id, postId, contentId, account, slot, lastError, reasonClass, coverage) so an agent knows exactly what it is retrieving. The tool is clearly a read/list of failed deliveries, distinguishable from the other listing siblings.

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?

Explains that state=open is both the tab view and the default, which tells the agent the no-arg call is the ordinary case, and it names the available filter dimensions. It also gives pagination procedure (follow cursor until null, pages can be short) and points to describe_tool for full details. It does not name an alternative sibling for taking action on a failed row (e.g. reschedule_post), so guidance stops short of explicit alternatives.

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