Shepherd MCP

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves data ('Get') and specifies the content included ('full details including input, output, usage, and costs'), which is helpful. However, it lacks critical behavioral details such as whether this is a read-only operation, error handling (e.g., for invalid IDs), authentication requirements, or rate limits. For a tool with no annotations, this leaves significant gaps.

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, efficient sentence that front-loads the core action ('Get a specific observation') and elaborates with essential details ('with full details including...'). There is no wasted text, and it directly communicates the tool's purpose without 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 the tool's low complexity (1 parameter, no nested objects) and high schema coverage (100%), the description is minimally adequate. However, with no annotations and no output schema, it fails to fully compensate for missing behavioral context (e.g., safety, errors) and output details. It provides basic purpose but lacks completeness for a tool that might involve data retrieval from an external service.

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%, with the single parameter 'observation_id' fully documented in the schema. The description adds no additional parameter semantics beyond implying that an observation ID is needed to fetch details. Since the schema already provides complete parameter information, the baseline score of 3 is appropriate, as the description doesn't enhance parameter understanding.

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 verb ('Get') and resource ('a specific observation') with scope ('with full details including input, output, usage, and costs'). It distinguishes from siblings like 'langfuse_list_observations' by specifying retrieval of a single observation rather than listing multiple. However, it doesn't explicitly contrast with other get tools like 'langfuse_get_session' or 'langfuse_get_trace'.

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 provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites like needing an observation ID, nor does it differentiate from other get tools (e.g., 'langfuse_get_session' for session-level data) or list tools (e.g., 'langfuse_list_observations' for multiple observations). Usage is implied but not explicitly stated.

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