Skip to main content
Glama
Sign In

Keytomic

by com.keytomic.app
OverviewDiscussionsAdmin

Update AI visibility prompt

update_visibility_prompt
DestructiveIdempotent

Changes one AI Visibility prompt of a site, the same as the prompt edit on the AI Visibility page. Pass text with expectedRevision (the revision from get_visibility) to edit the text, or state (active, paused or archived) to change the state, never both. Keytomic keeps or sets the topic and sets the prompt type of an edited text. A text edit of an Active prompt that changes the text or the prompt type makes a new prompt with a new promptId and archives the old one, which keeps its answers: use the promptId of the result in later calls. A text edit of a prompt that is not Archived and that changes neither, and a state change to the state the prompt already has (archived to archived too), change nothing and succeed. An Archived prompt cannot change otherwise. Refusals: prompt_revision_conflict (a change of an Archived prompt, or a text edit with an old expectedRevision that changes the text or the prompt type), active_prompt_limit_reached (making a prompt Active past the plan’s Active limit), prompt_duplicate (the new text is already saved for the market), saved_prompt_limit_reached, prompt_not_found (no such prompt in the market) and check_running (a check runs now). It starts no check.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>",
      "promptId": "<promptId>"
    },
    "name": "update_visibility_prompt"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoThe new text of the prompt. Needs expectedRevision.
stateNoThe new state of the prompt.
promptIdYesPrompt to change, from get_visibility.
projectIdYesSite to act on, from list_sites.
expectedRevisionNoWith text: the revision of the prompt that the user edits, from get_visibility.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description goes far beyond them: it explains the archive-and-recreate behavior on text edits to Active prompts, that the old prompt keeps its answers, that no-op edits succeed silently, that an Archived prompt cannot change otherwise, and that the call starts no check. It also lists the exact refusal codes. None of this contradicts the annotations; the idempotent no-op behavior and destructive archiving both align with them.

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?

The purpose and the mutual-exclusivity rule are front-loaded, and nearly every sentence carries operational meaning (revision semantics, no-op cases, refusal codes). It is a dense single paragraph, though, and the long refusal enumeration could be broken into a list for faster scanning.

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 five-parameter mutation tool with no output schema, the description is unusually complete: it covers revision semantics, state transitions, archiving, no-op outcomes, and refusal codes, and implies the result carries a promptId. The only meaningful omissions are the full shape of the success response and any permission or plan-tier requirements beyond the Active-limit refusal.

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 schema already documents each parameter, but the description adds real meaning: text requires expectedRevision, text and state are mutually exclusive, and expectedRevision must reflect the user-edited revision from get_visibility. The residual gap is small — the 10–500 character bound and the state enum values are left to the schema.

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 specific verb and resource: 'Changes one AI Visibility prompt of a site,' and anchors it to a known UI action ('the same as the prompt edit on the AI Visibility page'). This clearly distinguishes it from siblings like add_visibility_prompts or get_visibility, which add or read prompts rather than edit one.

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?

It gives explicit when-to-use conditions: pass text with expectedRevision to edit text, or state to change state, and 'never both.' It also enumerates refusal conditions, which implicitly define when the tool will not work. However, it never names an alternative sibling (e.g., where to add a new prompt instead), so the guidance stops short of full routing between tools.

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

All Keytomic 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