list_traces

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It clearly implies a read-only operation ('list and filter') and provides extensive behavioral details: supported filter operators, default time range (last 1 hour), page size limits (1-20), and a full list of response fields. This goes beyond a simple mutation tool and discloses what the agent can expect from the tool's behavior, though it does not mention side effects or authorization requirements (which are not applicable for a read-only list).

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 well-structured with clear sections (purpose, parameters, filters, examples, response fields) and an 'IMPORTANT' callout. However, it is fairly long (over 600 words). While every section adds value, some wording could be tightened, distinguishing it from a top-tier conciseness score but still being well-organized and front-loaded with the core purpose.

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?

Given the tool's complexity (7 parameters, a nested filters array, no output schema, no annotations), the description thoroughly compensates. It defines what a trace is, explains all filter operators and fields, gives examples, and enumerates response fields. It provides everything an agent needs to correctly invoke the tool, making it highly complete for a listing/filtering 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?

The input schema already covers all parameters (100% coverage), so baseline is 3. The description adds significant value beyond the schema: it explains the structure of the filters array, lists supported operators and fields, provides two concrete examples, and includes response fields. This enhances understanding of how to construct and use parameters, exceeding a mere restatement of schema descriptions.

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 tool's purpose: 'List and filter traces with sorting, pagination, and server-side filtering.' It specifies the resource (traces) and the actions (list, filter), distinguishing it from sibling tools like get_trace_tree (which retrieves a single trace tree) and get_spans_summary (which summarizes 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?

Provides explicit guidance: 'IMPORTANT: Use the "filters" parameter to filter results server-side. Do NOT fetch all traces and filter client-side.' This tells the agent when to use the filter parameter and warns against an anti-pattern. It also explains the trace concept and default time range, but does not explicitly contrast with alternative list tools, though the tool name and context imply its primary use case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.