Skip to main content
Glama
Sign In

SuperCatch

by com.supercatch
OverviewDiscussionsAdmin

Delete my saved search

supercatch_delete_saved_search
DestructiveIdempotent

Delete one exact account-owned saved search at its expected native version. The durable receipt remains inspectable; previously queued notifications cannot be recalled. Use only for an explicitly requested change to the authenticated account's saved searches. Resolve existing IDs and native versions with supercatch_list_saved_searches first. No seller inventory, prices, marketplace publication, payments, arbitrary filter JSON, alert enabling, email sending or automation changes. A strict account.saved_search.change operation with exact target and versions, local receipt, cache follow-up and native activity link. Existing deduplicated searches retain their current preferences. Requires OAuth account:saved_searches:write consent. Requires independent account:saved_searches:write consent and current account authority. Account reads and all seller write grants remain insufficient. No separate review is required for this exact low-impact saved change. Native activity shows committed receipts; disconnecting stops new connector changes. Operation keys and receipts have no automatic expiry in this release. Commits one account-owned saved-search change and its durable receipt in the same native transaction. New searches have notification and price-alert settings off. Cache invalidation follows the commit. Deletion cannot recall an already queued delivery. Missing consent, blocked/deleted accounts and foreign or stale targets fail closed. Keep the original high-entropy idempotency key; another intent on that key conflicts. After a lost response, recover with supercatch_list_operations using action account.saved_search.change and the original key, then inspect supercatch_get_operation. Do not create a replacement intent to recover a timeout.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "search_id": "owned-saved-search-id",
      "idempotency_key": "delete-search-example-001",
      "expected_version": "2026-11-04T16:00:00Z"
    },
    "name": "supercatch_delete_saved_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
search_idYesOpaque identifier returned by the authorized application; never substitute a display label or another entity's ID.
idempotency_keyYesStable client-generated key for this exact intent. Reuse it after a lost response; a different intent must use a new key.
expected_versionYesExact version returned by supercatch_list_saved_searches for this account-owned search. Changed versions require a fresh read.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover destructive/idempotent/closed-world, yet the description adds real substance: durable receipts stay inspectable, queued notifications cannot be recalled, OAuth account:saved_searches:write is required, and missing consent or stale targets fail closed. It is marred by leftover boilerplate that does not fit a delete ('New searches have notification and price-alert settings off', 'Existing deduplicated searches retain their current preferences'), which adds noise and slight confusion rather than contradiction of the annotations.

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

Conciseness2/5

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

The front-loaded purpose sentence is good, but the body repeats itself ('previously queued notifications cannot be recalled' then 'Deletion cannot recall an already queued delivery'; the OAuth consent requirement is stated twice) and includes sentences unrelated to deletion. Much of the text could be cut without losing call-relevant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, idempotent mutation with an output schema, the description covers safety, consent, recovery, and failure modes thoroughly. The only shortfall is the presence of create-oriented boilerplate that could mislead about what deletion actually affects.

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 100%, so all three parameters are already documented in the input schema. The description reinforces the idempotency key rule ('Keep the original high-entropy idempotency key; another intent on that key conflicts') and the version-freshness rule, but adds little beyond what the schema fields already state.

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 opening sentence names a specific verb and resource with scope: 'Delete one exact account-owned saved search at its expected native version.' That is clearly distinguishable from siblings like supercatch_create_saved_search, supercatch_update_saved_search_name, and supercatch_list_saved_searches.

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?

It states the qualifying condition ('Use only for an explicitly requested change to the authenticated account's saved searches'), a prerequisite lookup step via supercatch_list_saved_searches, and a recovery path via supercatch_list_operations and supercatch_get_operation. It also explicitly warns against creating a replacement intent to recover a timeout, which is genuine when-not guidance.

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

All SuperCatch 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