discover_adjacent_trends

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: the pipeline of embedding fetch, cosine-distance query, and especially the 'direct link exclusion filter', which tells the agent that directly connected trends are deliberately omitted and results are non-obvious. It still omits return format, ordering, and cost/rate behavior.

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?

Two sentences, front-loaded with the purpose before the parenthetical mechanics, with no filler. The internal-pipeline parenthetical is terse and slightly jargon-heavy, but it is compact rather than padded.

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 discovery tool with 8 fully documented parameters and no output schema, the safety profile and parameter meanings are adequately covered by annotations and schema. However, the description says nothing about how many/how results come back, how min_score interacts with limit, or the trial-tracking userId behavior, leaving meaningful gaps for an 8-parameter tool.

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 explains limit, query, seed_query, trend_id, min_score, and the rest. The description only loosely gestures at the seed-embedding step and adds no syntax, format, or precedence guidance (e.g. seed_query vs trend_id vs query) beyond what the schema provides. Baseline 3 applies.

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 names a concrete operation (vector-similarity graph traversal) and a concrete resource (adjacent, cross-domain trend patterns), so the agent knows it returns trends rather than nodes or claims. It does not, however, differentiate itself from siblings like get_neighbors or search_graph, which could plausibly surface similar-looking output. Clear verb+resource, but no sibling routing.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as an alternative. The agent must infer from the schema (seed_query vs trend_id) how to invoke it, but nothing tells it why it would pick this over search_graph, get_neighbors, or get_validated_trends.

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