Skip to main content
Glama

forget_references

DestructiveIdempotent

Delete stored reference patterns by exact ID or entire host. Use for takedown requests: permanently remove all records from a site, reporting skipped and failed items.

Instructions

Remove stored patterns from the local corpus — one by ref_id, or every pattern captured from a site. This is the takedown path: if a site asks that their design work not be kept, forget_references({ host: 'their.site', confirm: true }) removes every record and every rendered thumbnail from that host in one call. Host matching is exact plus subdomains ('linear.app' takes 'app.linear.app', never 'notlinear.app'; an IP address matches only itself), and a host-wide removal requires confirm:true because it is not reversible — there is no trash. The refusal names the ref_ids it would remove: pass them back as expected_ref_ids to pin the removal to what you were shown, and anything that appeared since is reported in appeared_since_preview[] rather than deleted. Returns the ref_ids actually removed, so a partial result is visible rather than assumed; records whose JSON could not be parsed are reported in skipped[] and left on disk rather than counted as cleared, and records that could not be deleted are reported separately in failed[]. Local only: it deletes files under the reference home and contacts nobody.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hostNoRemove every reference captured from this host and its subdomains, e.g. 'linear.app'
ref_idNoRemove exactly this one reference. Supply this or host.
confirmNoRequired when removing by host — the removal is permanent
expected_ref_idsNoThe ref_ids the confirmation prompt listed. Supplying them pins the removal to that set: anything matching the host that appeared since is reported, not deleted.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Addedv2.5.1

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations' destructiveHint, the description adds substantive behavioral context: irreversibility, no trash, exact host-with-subdomains matching, domain matching edge cases, local-only scope, and 'contacts nobody'. It also discloses response behaviors like appeared_since_preview, skipped, and failed results. No contradiction with annotations is present.

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

Conciseness5/5

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

The description is long, but every clause carries contractual detail: target mode, irreversibility, host-matching semantics, expected_ref_ids behavior, return channels, and edge cases. It is front-loaded with the essential action and structured to communicate complex destructive behavior without flat phrases.

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 compensates thoroughly by specifying every relevant return channel (ref_ids, appeared refused, skipped, failed) and the failure semantics (unparseable JSON, non-deletable records). It also covers all four parameters and the main destructive edge cases, so an empty element can execute it correctly and understand partial results.

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 coverage is full, and the description adds material meaning: exact-plus-subdomain matching, IP self-only matching, the reason confirm is required, and how expected_ref_ids pins the removal. This goes beyond the verbal Chinese 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?

The description opens with a clear verb-resource pair, 'Remove stored patterns from the local corpus', and explicitly distinguishes the two target modes: by ref_id or by host. It also names itself 'the takedown path', differentiating it clearly from capture/reference-search 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?

The description states exactly when to use the tool (site takedown, removing a single known ref, host-wide removal) and when host-wide removal requires confirm:true. It does not explicitly name an alternative non-destructive sibling, but the usage context and safety constraints are otherwise explicit and unambiguous.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rhinocap/raven-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server