langfuse-mcp-java

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

Description states 'Returns a paginated list...' implying a safe read operation, but annotations declare 'destructiveHint: true' and 'readOnlyHint: false', indicating a destructive write. This is a direct contradiction. Description fails to explain any destructive side effects if they exist.

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?

Front-loaded with the action, efficiently structured into purpose, return fields (compensating for missing output schema), and constraints. The return value list is useful given no output schema exists.

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?

Adequately compensates for the missing output schema by enumerating returned fields (id, name, metadata, etc.). Given simple scalar parameters and the presence of annotations (albeit contradictory), the description provides sufficient context for invocation.

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 coverage is 100% with clear descriptions for each parameter. The tool description groups pagination parameters and notes their defaults, matching the schema. With full schema coverage, this meets the baseline, though it adds no additional semantic context beyond what's in the schema.

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?

States specific action (Returns a paginated list) and resource (runs for a specific dataset), including domain context ('Each run represents one experiment'). Distinguishes from sibling 'get_dataset_run' by emphasizing the paginated list aspect.

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?

Mentions parameter constraints ('datasetName is required') and pagination defaults, but provides no guidance on when to use this versus 'get_dataset_run' or 'list_dataset_run_items', nor any prerequisites or error conditions.

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