Retrieve LLM traces for a project, filtering by status or limit to inspect and debug model performance.
Retrieve LLM traces for a project with optional filters.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max traces to return (default 50) | |
| status | No | Filter by status: ok, error | |
| project_name | Yes | Phoenix project name |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral transparency burden. It only says 'Retrieve', which implies read-only, but does not disclose output shape, ordering, pagination, or how filters affect results.
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 clear sentence with no waste. It front-loads the primary action and resource before mentioning filters.
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 input side is adequately covered by the schema, but no output schema exists and the description does not clarify return values. It also lacks sibling differentiation, so an agent may be unsure whether to choose get_traces or query_traces.
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 parameters are already documented. The description adds minimal semantic value beyond noting the existence of filters, which the schema already covers.
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 clear verb and resource: 'Retrieve LLM traces for a project' with optional filters. It distinguishes the tool by resource but does not explicitly differentiate it from siblings like query_traces or get_spans.
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 on when to use get_traces versus alternatives such as query_traces or get_spans. The phrase 'optional filters' is too generic to serve as usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.