Skip to main content
Glama
Sign In

Compoid MCP

by com.compoid
OverviewDiscussionsAdmin

Compoid_delete_record

Destructive

Delete a published Compoid record. IRREVERSIBLE.

The record is tombstoned and drops out of all search results. Use it to
clean up test records. Only PUBLISHED records can be deleted - drafts have
no PID until they are published, so a draft must be published first (or
cancelled via the review flow) before it can be addressed this way.

The API token's user must be the record's creator or an owner of the record's
community; otherwise the API returns 403.

Required:
    work_id: the record to delete - a published record PID (e.g.
        '4171t-rc787'), a full record URL
        (https://www.compoid.com/records/<pid>), or its OAI.

On success returns a confirmation (HTTP 204). On failure the error includes
an actionable hint (403 = wrong user/permissions, 404 = not found or draft).

Input Schema

NameRequiredDescriptionDefault
work_idYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true, but the description adds the substantive details an agent needs: tombstoning rather than hard removal, disappearance from search results, the creator/community-owner authorization requirement with a 403 outcome, and the 204 success signal. It also predicts failure modes with actionable hints.

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 destructive warning, then structured sub-paragraphs for constraints and parameters. It is longer than the minimum, and the return/error sentence partly duplicates the output schema, but every block carries usable decision information.

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 destructive, open-world, single-param tool this covers purpose, irreversibility, preconditions, auth requirements, accepted input forms, and success/failure semantics. An agent can invoke it correctly with no further reference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

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 parameter alone — and it does, enumerating all three accepted identifier formats (PID like '4171t-rc787', full record URL, or OAI) plus the constraint that the target must be published.

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+resource ('Delete a published Compoid record') and immediately scopes it to the published-only case, which distinguishes it from sibling update/create/delete-adjacent tools. The IRREVERSIBLE tag is front-loaded and unambiguous.

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 ('clean up test records'), an explicit when-not with the alternative path ('drafts have no PID... must be published first (or cancelled via the review flow)'), and names the permission precondition. 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 Compoid MCP toolsInspect
Try in Browser
Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources