deep_analyze

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

Annotations are absent, so the description carries full burden for behavioral disclosure. It only states the tool's purpose without mentioning side effects, permissions, rate limits, or output behavior. This is a critical gap.

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 sentence, concise but overly brief. It front-loads the purpose but sacrifices detail. While no words are wasted, the lack of structure and additional information reduces its utility.

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 has 2 parameters, no annotations, and sibling tools, the description is grossly incomplete. It fails to explain the role of the LLM, the meaning of 'MCP sampling', or how the output relates to the input, making it insufficient for an AI agent to use correctly.

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 0%, but the description does not compensate by explaining parameters. The parameter names (trace_id, question) are somewhat intuitive, but no additional semantics or constraints are provided, leaving uncertainty about valid values or formats.

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 states the tool is for 'LLM-assisted trace analysis' using 'MCP sampling', giving a general sense of purpose but lacking specificity on what makes it 'deep' versus other analysis tools. It does not differentiate from siblings like summarize_trace or analyze_errs.

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?

No guidance on when to use this tool versus alternatives. The description provides no context for decision-making, leaving the agent without criteria to select deep_analyze over sibling tools.

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