invoke_update_campaignUpdates only the supplied campaign fields.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Campaign ID to update. | |
| name | No | New campaign name. | |
| status | No | New campaign status. | |
| objective | No | New campaign objective. | |
| description | No | New campaign brief or notes. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, the description adds the important behavior that only the supplied fields are changed. This clarifies that unspecified fields are left as-is and that the call is not a full replacement or upsert. Annotations already indicate this is a non-read, destructive operation, and the description does not contradict them.
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?
One sentence with no filler. It front-loads the operation, the object, and the partial-update semantics. Every word adds value.
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?
For a small, non-nested update tool with fully documented parameters and annotations indicating destructive behavior and idempotency, the description covers the essential operational context. It could mention the return value, but in the absence of an output schema this is a minor gap.
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?
The input schema documents all five parameters with 100% coverage, so the schema already explains the fields. The description adds meaning by indicating that whatever fields are supplied apply as updates and that others are not affected, which clarifies the role of optional parameters and the required id.
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?
The description uses a specific verb ('Updates') and names the resource ('campaign fields') and clearly scopes it to a partial update ('only the supplied campaign fields'). This differentiates it from create-campaign and campaign-plan-item tools, though it does not explicitly name alternatives.
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?
The description provides no when-to-use guidance and does not mention alternatives or exclusions. An agent has to infer from the sibling names which update tool to choose, and for an operation with multiple 'update_*' siblings this is a notable gap.
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.
Most tools target a distinct resource and lifecycle state, so an agent can usually pick correctly. The main ambiguity is among the profile/context tools and the approve/schedule/publish family, but the descriptions give enough state-specific detail to avoid serious misselection.
The set consistently uses an invoke_ prefix with snake_case and mostly follows a verb_noun pattern. It only deviates with names like media_preflight and x_live_read, which place the verb at the end or use noun phrases.
With 33 tools, the server is well beyond the typical well-scoped range. It covers many distinct areas, but the high number of status-specific post tools and separate context/profile/workspace tools makes the surface feel bloated rather than cohesive.
The core social publishing workflow is covered well: create, edit, approve, schedule, publish, cancel, retry, and campaign planning. However, there are notable gaps such as no delete/archive for drafts, campaigns, or assets, and limited tools for inbox, comment, or broader analytics beyond the single X read gateway.