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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint. The description adds useful behavioral context beyond this on the output is a service of curated editorial connections that a web search cannot provide, and that a prior search_graph call is a prerequisite — which shapes how the agent sequences calls.

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 with the core purpose in the first sentence, followed by usage guidance. There is a small amount of redundancy between 'search alone wouldn't surface' and 'web search cannot provide', but it is overall effective and not overly wordy.

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 read-only traversal tool, the description adequately sets up expected inputs (node_id from search_graph) and output type (curated editorial connections), and the schema covers parameters in depth. The lack of an output schema and the omission of how to consume results is a minor gap, but the description still provides enough to invoke it correctly.

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 parameters are already fully documented in the input schema. The description does not add parameter-specific detail beyond the schema, but it reinforces the critical seed_node_ids requirement ('MUST be actual node_id values from a prior search_graph result'), which aligns with the schema's own emphasis.

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 states a specific verb (discover, returns) and resource (connections to a specific trend), and explicitly contrasts with 'search alone wouldn't surface' and 'search_graph'. This clearly distinguishes it from the sibling search_graph tool and conveys that it provides editorial connections.

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 explicitly says 'Use after search_graph to map the territory around a trend' and explains the kinds of questions it answers (brands, cross-domain relationships). It also states the shared condition ('Requires node_id from a prior search_graph result'). However, it does not explicitly say when not to use this tool or how it compares with siblings like get_node or get_evidence.

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