Create a Lever posting via POST /postings.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | JSON body to send to the documented Lever endpoint. | |
| reason | No | Reason for this Lever write. | Requested through Lever Ops Control Plane. |
| confirm | No | Set false only when you explicitly want to block execution. | |
| dry_run | No | When true, preview the write without sending it to Lever. | |
| perform_as | Yes | Lever user ID for perform_as when the Lever endpoint needs one. |
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?
Annotations are absent, and the description only says 'Create a Lever posting via POST /postings.' It does not disclose any side effects, permission requirements, idempotency, or response behavior, leaving the agent without critical context for a write operation.
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?
Single sentence of 8 words, zero filler, perfectly front-loaded. The description is appropriately sized and structured.
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?
The tool has five parameters and no output schema or annotations, yet the description is a bare one-liner. It does not explain the purpose of the body, the perform_as requirement, or the effects of dry_run and confirm, leaving the description insufficient for a complex creation operation.
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 coverage is 100%, with each parameter described (body, reason, confirm, dry_run, perform_as). The description adds no parameter information, but the schema already thoroughly documents them, so baseline 3 applies.
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 clearly states the action (create) and resource (Lever posting) with the HTTP method and endpoint, distinguishing it from sibling tools like update_posting and get_posting.
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 mention of when to use this tool versus alternatives; no exclusions or alternative tool references are given. The description provides no contextual guidance for selecting this tool.
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 distinct resource-action combinations, but the sheer count (108) and the presence of closely related tools like list_opportunity_feedback / get_opportunity_feedback may cause occasional agent confusion.
Tool names follow a highly consistent verb_noun pattern (e.g., create_*, get_*, list_*, update_*, delete_*, add_*, remove_*). Minor exceptions like apply_to_posting still fit the overall structure.
With 108 tools, the surface is excessively large for most agent workflows. Many tools could be merged or removed without losing essential functionality, leading to decision overload.
The tool set covers the full Lever API surface comprehensively, including opportunities, postings, requisitions, users, webhooks, templates, files, and compliance data, leaving no obvious gaps.