Skip to main content
Glama
Sign In

Convika

by com.convika
OverviewDiscussionsAdmin

Remove AI answer check questions

remove_answer_check_prompts
DestructiveIdempotent

Use this tool when the user wants to delete questions from their AI answer check (ChatGPT, Perplexity, Gemini, Google AI Overviews): 「この質問はもう聞かなくていい」「AI の回答チェックの質問を消して」, "stop checking this question", "delete these questions".

Deletes saved questions of the workspace's AI answer check, by id (get_answer_check_results' prompts) or by exact text. The results of every deleted question go too: its answers, whether they named the brand, the links they cited, and its history are no longer shown in the answer check's results and can't be brought back. Adding the same text again later starts a new question with no results. Checks already used aren't given back. Ask the user before deleting a question that has results.

  • Other saved questions stay as they are, with their results. Brand names and domains don't change.

  • An id or text that isn't a saved question deletes nothing (not_saved).

  • Two sites can save the same words: a text matching more than one deletes nothing (ambiguous_prompt). Send the id, or the host argument.

  • To change a question's wording: delete the old text here, then add the new text with update_answer_check_prompts.

  • expectedBrandId: with get_brand's id, a connection that now works on another workspace changes nothing (brand_mismatch). Returns changes (removed, kept) and the saved state, as get_answer_check_results does with no filter.

Input Schema

NameRequiredDescriptionDefault
hostNoOne of the workspace's sites, as get_brand's sites list it, such as 'www.sakura-cafe.com': only that site's questions are deleted or stay. Left out: the whole workspace's.
promptsYesSaved questions to delete, by id (get_answer_check_results' prompts) or by exact text; their results go with them
expectedBrandIdNoThe workspace's id from get_brand. When the connection now works on another workspace (the dashboard's active workspace was switched), the call changes nothing and answers brand_mismatch.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / host
      Added value: +{
+  "description": "One of the workspace's sites, as get_brand's sites list it, such as 'www.sakura-cafe.com': only that site's questions are deleted or stay. Left out: the whole workspace's.",
+  "maxLength": 253,
+  "minLength": 1,
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / expectedBrandId / description
      Previous value: -"The brand's id from get_brand. When the connection now works on another brand (the dashboard's active workspace was switched), the call changes nothing and answers brand_mismatch."New value: +"The workspace's id from get_brand. When the connection now works on another workspace (the dashboard's active workspace was switched), the call changes nothing and answers brand_mismatch."
  3. Added

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower. The description adds real value the annotations cannot: exactly what is destroyed (answers, brand-mention flags, cited links, history), that it is unrecoverable, that re-adding the same text starts with no results, and that checks already consumed aren't refunded. However, it does not mention required auth/permissions, rate limits, or batch-failure behavior (partial vs all-or-nothing when some prompts are invalid).

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 trigger sentence, followed by a compact bullet list of edge cases; the Japanese examples earn their space by disambiguating intent. It is on the long side for a delete tool and a few clauses (e.g., the host bullet) repeat schema wording, keeping it shy of a 5.

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?

No output schema exists, and the description covers it: it explains the return shape (removed/kept changes plus the saved state, like get_answer_check_results with no filter). Combined with idempotency and destructiveness annotations, the calling contract is clear; only auth/permission expectations are missing.

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; the description earns +1 by tying parameters to outcome semantics: prompts by id (from get_answer_check_results' prompts) or exact text, host scoping, and expectedBrandId producing brand_mismatch on workspace switch. It also supplies error codes (not_saved, ambiguous_prompt, brand_mismatch) that are not in the schema, though several phrases (id-or-text, host description) largely restate the schema text.

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 (delete) and resource (saved questions of the workspace's AI answer check) immediately, and explicitly distinguishes itself from get_answer_check_results (source of ids) and update_answer_check_prompts (add/rename). An agent can route between the three siblings without opening schemas.

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?

Front-loads a when-to-use trigger with multilingual example utterances, then gives concrete exclusions and alternatives: to change wording, delete here and re-add via update_answer_check_prompts; to disambiguate, send the id or host. It even adds a human-in-the-loop rule (ask before deleting a question with results).

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

All Convika 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