Update an existing agent in the system.
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": {
"data": "<data>"
},
"name": "agent_update"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | The agent data. |
Changes observed during successful MCP inspections.
Input schema / properties / data / descriptionAdded value: +"The agent data."Input schema / properties / data / requiredAdded value: +[
+ "agentId",
+ "firstName",
+ "lastName"
+]Input schema / properties / data / properties / about / descriptionAdded value: +"About information of the agent."Input schema / properties / data / properties / agentId / descriptionAdded value: +"Id of the agent."Input schema / properties / data / properties / email / descriptionAdded value: +"Name value of the email addresses. Name is the type of email address (e.g., \"work\", \"personal\"), and value is the email address itself (e.g., \"john.doe@example.com\")."Input schema / properties / data / properties / externalId / descriptionAdded value: +"External Id of the agent, pass in your id to associate this agent with your system."Input schema / properties / data / properties / fax / descriptionAdded value: +"Name value of the fax numbers. Name is the type of fax number (e.g., \"work\", \"personal\"), and value is the fax number itself (e.g., \"+1-555-555-5555\")."Input schema / properties / data / properties / firstName / descriptionAdded value: +"First name of the agent."Input schema / properties / data / properties / lastName / descriptionAdded value: +"Last name of the agent."Input schema / properties / data / properties / phone / descriptionAdded value: +"Name value of the phone numbers. Name is the type of phone number (e.g., \"work\", \"personal\"), and value is the phone number itself (e.g., \"+1-555-555-5555\")."Input schema / properties / data / properties / profileImageUrl / descriptionAdded value: +"Url of the agent profile image, this should be an external url."Input schema / properties / data / properties / public / descriptionAdded value: +"Indicates whether the agent's profile is public."Input schema / properties / data / properties / social / descriptionAdded value: +"List of social media links. Supported social media: Facebook, Twitter, Pinterest, Youtube, Vimeo, TikTok, Threads, Instagram. The value should be the url of the social media account."Input schema / properties / data / properties / social / additionalPropertiesRemoved value: -{
- "type": "string"
-}Input schema / properties / data / properties / social / anyOfPrevious value: -[
- {
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / data / properties / social / itemsAdded value: +{
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden, and it discloses almost nothing. It does not say whether omitted or null fields are cleared or left untouched, whether agentId must be an existing agent, whether this requires elevated permissions, or whether updates affect the published profile.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with zero filler. It is trivially concise, though the brevity comes at the cost of the missing semantics rather than through efficient compression of useful content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a mutation tool over a nested object with no annotations and no output schema, yet the description is one generic sentence. For a payload this shape (null unions, nested contact maps, externalId linkage), the definition leaves an agent guessing about merge semantics and side effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and every nested field (email, phone, social, externalId, public, profileImageUrl) is documented in the schema itself. The description adds no meaning beyond that, so the baseline of 3 applies; the real gap is that it does not clarify the null-vs-omit semantics that the anyOf types raise.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ("Update") and resource ("agent") plus the constraint that the agent must already exist. It is clear enough to separate from agent_add and agent_get_by_id by name alone, but it does not say which attributes are updatable or whether this is a full or partial update.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No when-to-use guidance at all: nothing about when to prefer this over agent_set_profile_image or agent_publish, no prerequisites, no mention of what happens if the agentId does not exist. The agent must infer everything from the tool name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.