Shepherd MCP

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

With no annotations provided, the description carries full burden. It discloses pagination behavior and filtering capabilities, which is helpful. However, it doesn't mention authentication requirements, rate limits, error conditions, or what the response structure looks like (especially important since there's no output schema). For a list operation with 8 parameters, more behavioral context would be beneficial.

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 extremely concise - just two sentences that efficiently convey the core functionality. The first sentence states the action with key behavioral aspects (pagination, filters). The second sentence provides helpful context about what traces represent. Every word earns its place with zero redundancy.

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 8 parameters, no annotations, and no output schema, the description provides basic but incomplete context. It covers the what (list traces) and some how (pagination, filters), but lacks information about authentication, error handling, response format, and performance characteristics. For a tool with this complexity and no structured output documentation, the description should do more to help the agent understand what to expect.

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 8 parameters thoroughly with descriptions and format hints. The description adds no additional parameter information beyond mentioning 'pagination and filters' generally. This meets the baseline of 3 when schema does the heavy lifting, but doesn't provide extra value like explaining parameter interactions or constraints.

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 action ('List traces') and resource ('traces'), and explains what traces represent ('complete workflows or conversations'). It distinguishes from siblings like 'langfuse_get_trace' (singular) and 'langfuse_search_traces' (search vs list). However, it doesn't explicitly differentiate from 'langfuse_list_sessions' or 'langfuse_list_observations' which are different resource types.

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 implies usage context through 'with pagination and filters' and the explanation of traces, suggesting this is for retrieving multiple traces with optional filtering. However, it doesn't explicitly state when to use this versus alternatives like 'langfuse_search_traces' (which might offer different search capabilities) or 'langfuse_get_trace' (for single trace). No explicit when-not-to-use guidance is provided.

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