Get recent individual AI/LLM calls with model, provider, tokens, cost, latency, and status. Helps answer 'what did my last AI calls look like?' or 'show me failed AI calls'.
| Name | Required | Description | Default |
|---|---|---|---|
| hours | No | Lookback hours (1-168, default 24) | |
| limit | No | Max results (1-200, default 50) | |
| model | No | Filter by model name (e.g., 'gpt-4o', 'claude-3-5-sonnet') | |
| provider | No | Filter by provider (e.g., 'openai', 'anthropic', 'workers-ai') |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses the tool returns individual calls with specific attributes and implies recency via 'recent' and the hours parameter. It does not disclose pagination behavior, ordering, or whether failed calls are included by default, but the schema covers the hours/limit mechanics. This is adequate but not rich.
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?
Two sentences, front-loaded with the core action and return fields, followed by concrete example queries. Every sentence earns its place and there is zero filler.
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 read-only list tool with 100% schema coverage and no output schema, the description covers what the tool returns and when to use it. It could mention ordering (e.g., newest first) or that failed calls are included, but nothing critical is missing for an agent to call it correctly.
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%, so the schema already documents all four parameters. The description adds the context that these parameters filter the returned call list, but it does not add meaning beyond the schema's own descriptions. Baseline 3 is appropriate.
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 a specific verb ('Get') and resource ('recent individual AI/LLM calls') and enumerates the exact fields returned (model, provider, tokens, cost, latency, status). It also gives example natural-language queries, which makes the tool's purpose unmistakable. It is clearly distinct from siblings like get_ai_summary or get_cost_summary, which aggregate rather than list individual calls.
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 gives concrete example questions ('what did my last AI calls look like?' or 'show me failed AI calls') that signal when to use this tool. It does not explicitly name alternatives or state when not to use it, but the examples plus the sibling names make the intended context clear enough.
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.
