LAWMADI

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

Annotations already declare this as readOnly, idempotent, and non-destructive. The description adds valuable behavioral specifics: it returns exactly '3' questions and explains the contextual basis (query + specialty). It does not contradict annotations. However, it could clarify whether these suggestions are pre-computed or generated, and whether they persist.

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 core description is efficiently front-loaded ('Suggest 3 contextual follow-up questions...'), but the description suffers from excessive auto-generated HTTP response schema documentation (### Responses, 200/422 codes, JSON examples) that adds noise without aiding tool selection. The useful signal is buried under verbose OpenAPI-style response documentation.

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?

Despite the output schema being empty ({}), the description compensates by explicitly stating the tool returns '3' suggested questions. For a simple, read-only tool with 3 well-documented parameters, the description provides sufficient context for invocation, though it could briefly note that results are ephemeral/read-only.

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 baseline is appropriately met. The description references 'current query and leader specialty' which maps to the parameters, but adds no semantic details beyond the schema's own descriptions (e.g., doesn't explain the Korean examples '담우' or '노동법' or how they influence suggestions).

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 it 'Suggest[s] 3 contextual follow-up questions based on the current query and leader specialty.' This provides a specific verb (suggest), resource (questions), and scope (3 contextual follow-ups). It implicitly distinguishes from sibling tools like 'ask' or 'chat' by focusing on suggestion generation rather than answering or conversation.

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 (generating follow-ups based on current query), but provides no explicit when-to-use guidance or comparison to alternatives. It does not clarify when to use this versus continuing with 'ask' or 'chat' tools, leaving the agent to infer that this is specifically for generating next-question suggestions.

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