Adaptive Search (Jev)

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

Even though readOnlyHint=true, openWorldHint=true, and destructiveHint=false are present, the description adds substantial behavioral context beyond annotations: only Jev-approved results are returned, approval is a model judgement rather than verified truth, results are ephemeral (30 minutes/32 runs), UTC semantics for relative dates, credential requirements and not_configured behavior, and data routing to the configured Jev service. This is far above the annotation baseline.

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 dense but every sentence contributes distinct value: mode selection, limits, batching, result semantics, pagination warnings, data retention, credentials, privacy, and sibling routing. It is front-loaded with the core purpose before diving into constraints, and there is no filler or redundant restating of the tool name.

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?

For a complex multi-mode search tool with an output schema, the description is remarkably complete: it covers all input modes, cardinality limits, pagination behavior, approval semantics, result freshness, timezone handling, auth failure behavior, data-sending implications, and when to choose alternatives. Nothing material needed to invoke it correctly is left unexplained.

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 description coverage is 100%, so the baseline is 3. The description adds meaningful parameter-relationship semantics: tasks and questions are mutually exclusive modes, cursor must be used without tasks/questions, and page_size defaults to 20 with no fixed cap on approved results. This goes beyond the individual schema property descriptions, earning a 4.

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 a specific operation: 'Jev-driven keyword-target research' with tasks, targets, or legacy questions as input. It also explicitly differentiates itself from sibling tools by saying 'Prefer fused_search for a precise lookup, fetch_page for a known URL and x_search for X-specific retrieval,' so an agent can disambiguate immediately.

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 gives strong when-to-use and when-not-to-use guidance: supply tasks with targets, or legacy questions, but not both with cursor; follow nextCursor to read more; and prefer other sibling tools for different lookup types. It also warns that pagination is not exhaustive and to inspect coverageComplete and warnings, which shapes the calling strategy.

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