langfuse-mcp-java

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

Adds valuable behavioral context not in annotations: the 500-trace scan limit and response structure (errorCount, timestamps). However, fails to explain why the tool is marked destructiveHint:true and readOnlyHint:false, which is confusing given the 'get'/read-oriented description.

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?

Five sentences with zero waste: purpose first, then implementation limits, response format, parameter optionality, and usage guidance. Front-loaded and efficiently structured.

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?

Comprehensive coverage including scan limits, response contents (compensating for missing output schema), and parameter behavior. Minor gap: does not clarify the destructive nature of the operation or potential rate limits.

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 has 100% coverage (baseline 3). The description adds important semantic detail that parameters are optional and can be omitted for all-time counts, though this appears to contradict the schema's 'required' field.

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 opens with a clear specific verb ('Returns') and resource ('ERROR-level traces'), and explicitly distinguishes from sibling tool 'find_exceptions' by stating this is for 'quick health signal' before drilling into individual traces with that 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?

Provides explicit guidance on when to use ('quick health signal') versus when to use the alternative ('drilling into individual traces with find_exceptions'). Also clarifies parameter optionality behavior ('Omit them to count errors across all time').

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