Skip to main content
Glama

update_profile

Destructive

Update profile fields.

Health conditions change via add_/remove_health_conditions (remove must match a stored entry verbatim); the other list fields (supplements…) replace the whole list.

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": {
      "profile": "<profile>"
    },
    "name": "update_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
profileYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / $defs / UserProfileUpdate / additionalProperties
      Added value: +false
    • addedInput schema / $defs / UserProfileUpdate / properties / add_health_conditions
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Health conditions to add to the stored list. Stored entries not named in remove_health_conditions are always kept.",
      +  "title": "Add Health Conditions"
      +}
    • removedInput schema / $defs / UserProfileUpdate / properties / health_conditions
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "items": {
      -        "type": "string"
      -      },
      -      "type": "array"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "description": "List of user's health conditions",
      -  "title": "Health Conditions"
      -}
    • addedInput schema / $defs / UserProfileUpdate / properties / remove_health_conditions
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Stored health conditions to remove, each copied verbatim from the stored list. To update an entry, remove the old string and add the new one in the same call.",
      +  "title": "Remove Health Conditions"
      +}
  2. Changed1 schema field changed
    • changedInput schema / $defs / UserProfileUpdate / properties / language / description
      Previous value: -"User's preferred language"New value: +"Language the coach writes in, as a BCP 47 tag (e.g. 'de-DE', 'sl-SI', 'en-US')"
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, and the description earns its keep by explaining exactly what gets destroyed: non-health list fields (supplements, interests, etc.) are wholesale replaced, while health conditions are additive/subtractive with verbatim removal matching. The significant undisclosed behavior is how null or omitted fields are treated for the ~20 scalar fields on a destructive update, which is left silent.

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?

Two tight sentences with the verb and the highest-risk behavior front-loaded; nothing is padded. The parenthetical "(supplements…)" is slightly vague about which list fields fall in the replace category, but the point survives.

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

Completeness3/5

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

For a destructive, 20-plus field updater, the description covers the list-field semantics well and an output schema covers return values, but it never addresses partial-update behavior — whether omitting a field preserves it and whether passing null clears it. That omission is material for a tool annotated as destructive.

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?

Although the top-level 'profile' parameter carries no description, the description supplies semantics the schema does not: that one group of list fields replaces entirely while health conditions use add/remove and require exact string matches. That distinction directly governs how an agent must populate the parameters and prevents accidental data loss.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Update profile fields"), which an agent can immediately distinguish from get_profile. It does not explicitly name the read-side sibling or other write tools, but the intent is unambiguous.

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?

Gives concrete procedural guidance for the one tricky case: health conditions must be changed through add_health_conditions/remove_health_conditions rather than a direct list, and removals must match stored entries verbatim. It stops short of stating when to prefer this tool over siblings or what to do for a full reset.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources