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

Annotations already establish readOnlyHint, openWorldHint, and non-destructive behavior, lowering the bar. The description adds substantial behavioral context by specifying the parallel search over all accessible graphs when graphId is omitted and by describing the return value shape: trend data with cited evidence, source attribution, and lifecycle stage. This goes beyond what the annotations alone convey.

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 concise and front-loaded, stating the core purpose in the first sentence and then adding default behavior and use cases. Every sentence contributes value, and there is no filler or repetition. It remains easily scannable for an AI agent choosing a tool.

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 tool with 9 parameters and no output schema, the description provides high-level output expectations (cited evidence, attribution, lifecycle stage) and default behavior. It integrates well with the comprehensive schema, though it does not serve to explain what each of the more nuanced parameters like mode or graphs does. With schema coverage at 100%, this is sufficiently complete.

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%, and all parameters already have detailed descriptions in the schema. The tool description does mention the graphId default and that omitted graphId searches all graphs, but this information is also present in the schema. Since the schema carries the full burden, the description adds no significant extra param semantics beyond the baseline.

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 opens with a specific verb and resource: 'Find trends, signals, and expert insights across 100+ curated knowledge graphs.' It clearly distinguishes itself from generic web search by noting that it returns cited evidence and lifecycle stage, not generic web summaries. However, it does not explicitly differentiate among sibling search tools like search_insights or search_statistics.

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?

Provides clear guidance on when to use the tool: 'Use for market trends, competitor analysis, innovation signals, consumer behavior, cultural shifts, or any topic where curated expert intelligence outperforms web search.' It also gives a strong default recommendation to omit graphId and search all graphs. Missing explicit exclusions with respect to alternative sibling tools.

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