Full diagnostic: loop detection, cost breakdown, stuck-state classification, and fix recommendations for an AI agent trace.
| Name | Required | Description | Default |
|---|---|---|---|
| trace | Yes | Ordered array of agent steps (role, tool, input, output, tokens, model) | |
| pricing | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It does disclose the main analytical behaviors (loop detection, cost breakdown, stuck-state classification, fix recommendations), but it does not explicitly state that the tool is read-only, describe any side effects, or mention permissions/rate limits. This leaves some behavioral aspects implicit.
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 a single sentence that front-loads the core purpose with 'Full diagnostic' and immediately lists the specific diagnostic components. Every phrase contributes meaning, with no filler or repetition, making it highly concise and well-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?
This is a complex tool with multiple diagnostic outputs and no output schema, yet the description does not explain the return format, how fix recommendations are presented, or the expected shape of the pricing input. Given the absence of annotations and output schema, the one-line description is insufficient for an agent to fully anticipate the tool's behavior and outputs.
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 trace parameter is described in the schema, but the pricing parameter has no schema description and the tool description only indirectly references it via 'cost breakdown.' The description does not compensate for the 50% schema coverage gap by explaining the pricing object's meaning or optionality, leaving its semantics unclear.
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 opens with 'Full diagnostic' and enumerates specific capabilities: loop detection, cost breakdown, stuck-state classification, and fix recommendations. This clearly identifies the resource (AI agent trace) and scope, and distinguishes it from the focused siblings breakdown_cost and detect_loops by covering both analyses plus additional diagnostics.
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 phrase 'Full diagnostic' implies use when a comprehensive analysis is needed, but the description does not explicitly state when to prefer this tool over the siblings or when not to use it. No alternatives are named, so guidance is only implied rather than made explicit.
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.
The tools have clear granularity distinctions: analyze_trace is the comprehensive diagnostic, while detect_loops and breakdown_cost target specific aspects. However, analyze_trace overlaps with both specialized tools, which could cause an agent to hesitate between calling it or the more specific one. The descriptions mitigate this by stating the scope explicitly.
Three tools use snake_case, but while analyze_trace and detect_loops follow a verb_noun pattern, breakdown_cost is a compound noun phrase, deviating from the verb-first style. The naming is otherwise consistent and readable.
With only three tools, the server stays focused on its stated purpose of trace analysis. Each tool serves a distinct role, and the count feels appropriate for a specialized utility.
The server covers loop detection, cost breakdown, and comprehensive diagnostics including stuck-state and recommendations. No obvious gaps exist for the domain, as the full diagnostic subsumes the specialized functions.