langfuse-mcp-java

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

The description characterizes this as a read operation ('Returns'), which directly contradicts the annotations declaring `destructiveHint: true` and `readOnlyHint: false`. This inconsistency makes it impossible to trust the described safety profile.

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 four sentences are well-structured and front-loaded: purpose (list), return structure (fields), business context (human-in-the-loop), and pagination mechanics. Each earns its place, though the field enumeration could be more concise.

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 no output schema exists, the description adequately compensates by enumerating returned fields (id, name, description, etc.) and explaining the business purpose (human-in-the-loop workflows). It covers the essential behavioral contract for a paginated list 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?

Despite 100% schema coverage, the description adds crucial semantic context: clarifying that pagination is '1-based' (not 0-based) and restating default values (page=1, limit=20) that might otherwise be buried in schema defaults.

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 'Returns a paginated list of annotation queues' with specific resource and scope (Langfuse project). It distinguishes from sibling `get_annotation_queue` (singular) by emphasizing pagination and listing multiple items, though it doesn't explicitly name the alternative.

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 implied usage through pagination guidance ('page is 1-based', default values), but lacks explicit guidance on when to use this listing tool versus `get_annotation_queue` for single-record retrieval or filtering capabilities.

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