LAWMADI

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

The description adds valuable behavioral context beyond annotations by specifying the SSE streaming nature and statute verification feature—critical for an AI agent to understand this isn't a standard request-response tool. Annotations cover safety (readOnly, non-destructive) but the description explains the actual delivery mechanism.

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 suffers from significant bloat with auto-generated HTTP response documentation (status codes, content-types, example JSON, error schemas) that consumes most of the text. Only the first sentence provides actionable tool selection context. The structural information should be front-loaded or omitted in favor of usage guidance.

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?

While the streaming behavior is explained, the description omits guidance on the complex leader interaction modes (general vs. leader_chat vs. expert) and when to use current_leader versus leader_id parameters. Given the nested object complexity and lack of output schema for the success case, additional context on the response format or session state management would improve completeness.

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?

With 100% schema description coverage, the input parameters are fully documented in the schema itself (query limits, mode options, leader context). The description text adds no parameter semantics, which is acceptable given the comprehensive schema, meeting the baseline score of 3.

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 identifies the core action (SSE streaming legal question) and key features (real-time token-by-token response with statute verification). It distinguishes itself from siblings through the streaming mechanism, though it could explicitly contrast with ask_ask_post to clarify when streaming vs. complete responses are preferred.

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 through 'SSE streaming' and 'real-time' keywords, suggesting use for live response scenarios. However, it lacks explicit when-to-use guidance versus ask_ask_post (non-streaming) or ask_expert_ask_expert_post, and doesn't explain the leader handoff workflow despite having parameters for it.

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