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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's added value is real: a hard 200-flow scope cap, a 2+ flow minimum for AI mode, and the fact that use_ai consumes one AI insight run from the plan. That cost/quota disclosure is exactly the kind of behavioral context annotations cannot 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?

Front-loads the core behavior, then the AI mode and its constraints. Three dense sentences with no filler, though the opening enumeration of seven pattern categories is long and could be trimmed slightly.

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?

There is no output schema, so the description carries the return-shape burden and largely meets it by naming the finding categories, plus limits and quota cost. Only minor gaps remain (e.g., what 'flagged' or 'due for a check-in' concretely mean, or any pagination/limit on results).

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 coverage is 100% and the schema already states the default false, so the baseline is 3. The description goes beyond it by explaining what use_ai actually adds (AI patterns with flows as evidence plus questions for follow-up calls) and its two preconditions, which is meaningful extra semantics.

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 ('Find patterns') over a specific, bounded resource ('across every flow the user owns or can edit, up to 200 flows'), then enumerates the exact pattern categories returned. That cross-flow aggregation scope cleanly separates it from list_flows, search_flows, query_flows, and summarize_flow without needing the sibling schemas.

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?

It gives the condition for the optional AI mode ('Set use_ai to true to also get AI patterns') and its prerequisites ('needs two or more flows'). It does not explicitly say when to prefer get_insights over search_flows/query_flows/summarize_flow, so it stops short of naming alternatives.

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