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

Annotations already carry the safety profile (readOnlyHint=true, destructiveHint=false), so the description's job is to add context beyond that. It does: it discloses output composition ('trend data with cited evidence, source attribution, and lifecycle stage — not generic web summaries') and a significant runtime behavior ('searches ALL accessible graphs in parallel'). This is meaningful behavioral context an agent needs before calling, and it doesn't repeat the annotations.

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?

Three sentences do the full job: what it finds, what the output is AND what it is not, and the recommended invocation chain. The 'not generic web summaries' contrast assignment is given before the use-case list. Every sentence earns its space — well front-loaded for an agent.

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 9-parameter tool with no output schema, the description covers the essentials: the semantics of the output (trends, evidence, attribution, lifecycle), the default search behavior across all graphs, and the use cases. The schema covers all parameter-level details. It could be '5' if the description referenced the output shape or the graphs available, but given the schema is fully self-descriptive and the omission is partial, a '4' is appropriate.

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 schema already documents all 9 parameters (mode enum, graphs precedence rule, unavailable_graphs reporting, graphId examples). The description adds no new per-parameter semantics except reaffirming missing graphId searches all graphs, which the schema already states. Baseline 3 is appropriate — no gaps but no added value.

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 uses a specific verb and resource ('Find trends, signals, and expert insights across 100+ curated knowledge graphs covering retail, beauty, tech, food, travel, sports, and 30+ specialist domains') and clearly differentiates the output from generic web search ('not generic web summaries', 'curated expert intelligence outperforms web search'). It does not explicitly name and distinguish sibling tools, but the contrast with web search and the explicit return payload (citations, source attribution, lifecycle stage) give a strong positional identity.

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?

Spells out concrete use cases: 'market trends, competitor analysis, innovation signals, consumer behavior, cultural shifts'. It also gives a strong default-behavior guideline ('If graphId is omitted, searches ALL accessible graphs in parallel (recommended default)') that tells the agent how to invoke it by default. No exclusions or sibling alternates are named, so '5' is not justified, but the guidance is clear enough for selection.

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