post_moderationsClassifies if text is potentially harmful. Group: Moderations. Billing per call: Credits: metered.
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | JSON request body. Example: {"model":"text-moderation-latest","input":"Today is a wonderful day to build something people love!"} |
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?
With no annotations, the description must carry transparency. It mentions billing (Credits metered) and group label, but fails to disclose any behavioral traits like whether changes are made, side effects, rate limits, or the nature of the response. It implies a read-only classification but does not explicitly state it. The lack of safety or side-effect information is a gap.
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 compact, two sentences, with the primary purpose in the first sentence. The billing/group metadata is concise, though it could be considered extraneous. It is front-loaded with the essential action, making it easily scannable.
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 description is brief and does not explain the output format, categories of harm, input constraints, or any error conditions. Given that this is a POST endpoint with a nested object and no output schema, the description should provide more context (e.g., what the response contains, max input length). It is incomplete for an agent to use effectively without additional 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?
Schema description coverage is 100% because the single 'body' parameter includes an example. The description adds no extra meaning beyond the schema—it doesn't explain the structure of 'body' or any constraints. Baseline of 3 is appropriate since the schema manages the parameter documentation adequately.
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 states the tool classifies text for potential harm, which is a specific verb+resource. It differentiates from sibling tools (chat, embeddings, models) as a distinct moderation classification. However, 'Create Moderation' is a slightly misleading title since the tool doesn't create anything persistent; the purpose is clarified but not fully precise.
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 guidance on when to use this tool versus the sibling tools (e.g., chat completions, embeddings). No conditions, prerequisites, or exclusions are given. The agent must infer from the name and purpose that it's for moderation, but no explicit alternatives or scenarios are mentioned.
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.
Each tool serves a completely distinct API endpoint: listing models, creating chat completions, generating embeddings, and moderating text. There is no overlap or ambiguity between the operations, making it clear which tool to select for a given task.
All tools follow a consistent verb_noun pattern using HTTP methods (get_ or post_) followed by the resource in snake_case (e.g., get_models, post_chat_completions). The naming is uniform and predictable.
With only 4 tools, the server is concise and well-scoped for its purpose of wrapping a core AI API surface. Each tool covers a fundamental operation (list, chat, embeddings, moderation) without unnecessary bloat.
The toolset covers the primary interactions with a typical AI API: listing models and generating completions, embeddings, and moderation scores. A minor gap is the lack of a single-model GET endpoint, but the current coverage handles core workflows effectively.