Skip to main content
Glama
Sign In

LinkGPT

by app.linkgpt
OverviewDiscussionsAdmin

Change the AI Profile

update_ai_profile
Destructive

Changes the user's public AI Profile, the page AI engines read: profile text (tagline, bio, role, expertise, mission, audience, what makes them different, call to action), Q&As or featured content. You write the new text. mode apply (the default) makes the change now: use it when the user asked for this change or said yes to it. mode review saves it to Ready to apply in the Action Center without changing anything: use it when the user wants to look later or isn't in the conversation. Returns the before and after, and a changeId for undo_change.

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": {
      "change": "<change>"
    },
    "name": "update_ai_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoapply (default): make the change now. review: save it for the user to approve later.
titleNoA short title, if the default isn't clear.
changeYes
reasonNoWhy this helps, in a sentence, citing the data you used. Shown in the Action Center.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the destructiveHint/readOnly annotations, the description discloses that review mode writes to 'Ready to apply' in the Action Center without touching anything, that the response returns before and after plus a changeId wired to undo_change, and that Q&As cap at 12 total. These are precisely the mutation-safety details annotations alone cannot convey.

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 resource and its contents, then mode semantics, then return shape. Dense but every clause (field list, mode guidance, undo handle) carries information an agent needs. The long parenthetical field list is the only mildly bulky element.

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?

A four-parameter mutation tool with a nested oneOf schema and no output schema, yet the description covers what gets changed, both execution modes, limit constraints, and the return payload including the undo handle. Nothing material is missing for correct invocation.

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 75%, so most fields already carry descriptions with character limits. The description still adds real meaning beyond the schema: it labels the field group as profile text, clarifies 'You write the new text', and ties changeId output to the undo_change workflow, which the schema does not connect.

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 states a specific verb and resource ('Changes the user's public AI Profile') and then enumerates exactly what is mutable: profile text fields, Q&As, and featured content. That level of enumeration lets an agent distinguish it from read-only siblings like get_profile without opening the schema.

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 conditions for both modes: apply 'when the user asked for this change or said yes to it', review 'when the user wants to look later or isn't in the conversation'. It also instructs the agent to author the new text. It never names a sibling tool for the read/compare path (e.g. get_profile or approve_changes), which keeps it short of a full 5.

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

All LinkGPT 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