Skip to main content
Glama

pinbridge

by io.pinbridge
OverviewDiscussionsAdmin

Update unpublished pin

update_pin
DestructiveIdempotent

Edit a pin that has NOT been published yet: title, description, link, alt text or board.

    Use to fix a typo, link or board before the pin publishes: queued,
    deferred and failed pins then publish with the new values. Published
    pins cannot be edited: Pinterest's API does not allow PinBridge to
    change a pin once it is live, so the call fails with
    pin_already_published. For a published pin, offer delete_pin plus a
    new create_pin (confirm first). To change the image use delete_pin then
    create_pin; for a failed pin on a bad board use retry_pin. Pass at
    least one field.

    Returns the updated pin. Fails with pin_already_published for a
    published pin, not_found for an unknown id, and conflict
    (pin_publishing) while the pin is mid-publish. A new board is
    preflighted like create_pin.

Input Schema

NameRequiredDescriptionDefault
titleNoPin title, at most 100 characters.
pin_idYesUUID of the pin, from list_pins or create_pin.
alt_textNoNew accessibility text, <= 500 characters.
board_idNoPinterest board ID (numeric string), from list_boards.
link_urlNoDestination URL opened when the pin is clicked.
descriptionNoPin description, at most 800 characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / alt_text / description
      Added value: +"New accessibility text, <= 500 characters."
    • addedInput schema / properties / board_id / description
      Added value: +"Pinterest board ID (numeric string), from list_boards."
    • changedInput schema / properties / description / anyOf
      Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maxLength": 800,
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / description / description
      Added value: +"Pin description, at most 800 characters."
    • addedInput schema / properties / link_url / description
      Added value: +"Destination URL opened when the pin is clicked."
    • addedInput schema / properties / pin_id / description
      Added value: +"UUID of the pin, from list_pins or create_pin."
    • changedInput schema / properties / title / anyOf
      Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maxLength": 100,
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / title / description
      Added value: +"Pin title, at most 100 characters."
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations, it discloses the failure modes by name (pin_already_published, not_found, conflict pin_publishing mid-publish), that a new board is preflighted like create_pin, that queued/deferred/failed pins republish with new values, and that it returns the updated pin. This is context the destructiveHint/idempotentHint annotations cannot convey.

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 core purpose and organized into purpose / usage / side-effects / returns paragraphs. It is longer than average but nearly every sentence carries distinct, actionable information (error names, alternatives), with only minor repetition of the 'not published' constraint.

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, the description carries the return burden and does so ('Returns the updated pin') and enumerates each failure condition. For a mutation tool with siblings that overlap heavily, all the routing and failure context an agent needs is present.

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 a real constraint not in the schema: 'Pass at least one field' (schema only requires pin_id). It also reiterates which fields are editable and flags board preflight, giving marginal meaning beyond the field-level schema descriptions.

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 verb (edit), resource (pin), and a hard scope constraint (NOT yet published), then enumerates the editable fields. It explicitly distinguishes itself from the published-pin path, so an agent can tell it apart from delete_pin/create_pin without opening any schema.

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 when-to-use (fix a typo/link/board pre-publish), when-not (published pins cannot be edited), and named alternatives for each case: delete_pin + create_pin for published pins or image changes, retry_pin for a failed pin on a bad board. Nothing is left to inference.

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

All pinbridge 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