GET /inbox/items
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Optional query overrides for endpoints with sparse parameter schemas. | |
| cursor | No | ||
| brand_id | No | ||
| workspace_id | No | Workspace to operate in. Do not ask the user for this UUID — call aidelly_list_workspaces and use the `id` of the matching workspace. Optional for read operations; required when creating content. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / cursorAdded value: +{
+ "maxLength": 512,
+ "type": "string"
+}Input schema / properties / workspace_id / descriptionAdded value: +"Workspace to operate in. Do not ask the user for this UUID — call aidelly_list_workspaces and use the `id` of the matching workspace. Optional for read operations; required when creating content."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. However, the description adds no behavioral context beyond the endpoint: it does not disclose that this returns a list of inbox items, that it supports pagination via the cursor parameter, or what response format to expect. The description fails to leverage the opportunity to explain behavior beyond what annotations already state.
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?
The description is extremely short but this is under-specification, not effective conciseness. It consists of a single line that provides no additional information beyond the tool name. There is no front-loading of key information because there is no meaningful content at all.
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?
With 4 parameters, no output schema, and many sibling tools, this description is wholly inadequate. It does not explain what 'inbox items' are, how to use the cursor for pagination, how filtering works, or any details about the response. An agent would have no confidence in invoking this tool correctly without external documentation.
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 has 4 parameters, with descriptions on 'query' and 'workspace_id' (50% coverage). The description 'GET /inbox/items' adds zero parameter semantics. It does not explain the 'cursor' for pagination, 'brand_id' for scoping, or the role of the 'query' override object. Since schema coverage is not high, the description should have compensated but did not.
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 is merely 'GET /inbox/items', which is essentially a restatement of the tool name in HTTP format. It does not explicitly state what the tool does ('retrieves inbox items') nor does it distinguish it from other 'get_' tools beyond the name. This is closer to a tautology than a clear purpose statement.
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 guidance is provided about when to use this tool, what alternatives exist, or any contextual prerequisites. The description lacks any comparison to sibling tools like aidelly_list_posts or other get_* operations, leaving the agent to guess based on the endpoint path alone.
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.
Many tools have overlapping purposes, especially in approvals and post updates. For example, aidelly_action_post_approval and aidelly_post_approvals_id_action both handle approval actions, while aidelly_get_approvals and aidelly_list_pending_approvals appear to serve similar listing functions. The proliferation of HTTP-route-style names with generic prefixes (get_approvals_id, patch_posts_id) further obscures distinctions.
The tool set mixes clean verb_noun names (create_post, list_posts) with HTTP-method-plus-path names (get_approvals_id, patch_posts_id, post_analytics_insights). There is no consistent pattern, and 'post' as a verb collides with the content post noun, creating confusion. The inconsistent conventions make it hard to predict tool names.
With 124 tools, this server vastly exceeds the typical MCP server scope and the calibration threshold (50+ is extreme). Even for a comprehensive platform API, such a large surface overwhelms agents and makes selection impractical. The count is a severe mismatch for a usable MCP tool set.
The tool surface is remarkably comprehensive, covering CRUD for posts, drafts, scheduled posts, tasks, reports, webhooks, workspaces, e-commerce stores, and many more. Advanced features like approvals, repurpose jobs, and content automations are also represented. Minor gaps exist (e.g., no explicit delete for regular posts, only cancel), but the domain is well covered overall.