Shepherd MCP

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

No annotations are provided, so the description carries full burden for behavioral disclosure. While it details what aspects are compared, it doesn't mention how differences are presented (e.g., structured output, visual diff), whether it's read-only or has side effects, performance considerations, or error handling for invalid session IDs. For a comparison tool with zero annotation coverage, this leaves significant behavioral 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, well-structured sentence that front-loads the core purpose ('Compare two AI agent sessions and show their differences') followed by a comprehensive list of compared aspects. Every element earns its place by specifying the scope without redundancy, making it highly efficient and easy to parse.

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 complexity (comparing multiple session aspects) and lack of annotations/output schema, the description provides a good overview of what's compared but is incomplete. It doesn't cover behavioral traits (e.g., read-only nature, error handling) or output format, which are crucial for an AI agent to use it correctly. The description is adequate as a starting point but has clear gaps for full contextual understanding.

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?

The input schema has 100% description coverage, with both parameters clearly documented as session UUIDs. The description doesn't add any parameter-specific details beyond what the schema provides (e.g., format examples, validation rules). According to scoring rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no param info in the description, which applies here.

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 specific action ('Compare two AI agent sessions and show their differences') and the comprehensive scope of comparison ('including metadata, LLM calls, tokens, latency, providers, models, functions, evaluations, errors, system prompts, request parameters, and response content'). It distinguishes this tool from sibling tools like aiobs_get_session (retrieves single session) and aiobs_list_sessions (lists multiple sessions) by focusing on comparative analysis.

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 the phrase 'Compare two AI agent sessions,' suggesting this tool is for side-by-side analysis rather than individual session retrieval. However, it doesn't explicitly state when to use this versus alternatives like diff_sessions (a sibling with similar name) or provide exclusion criteria (e.g., when sessions are too dissimilar). The guidance is present but not explicit about alternatives or limitations.

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