get_ai_insights

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the qualitative/narrative nature of the output and the conceptual categories returned, which is useful context beyond the schema. However, it does not state permissions, rate limits, cost/latency of AI analysis, or whether results are computed on-demand or cached.

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 bracketed purpose tag, then best-for/not-for, then example questions. Well structured and mostly tight, though the four example questions are somewhat redundant with the 'Best for' section and add length without much new information.

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?

With no output schema, the description responsibly sketches the return categories (tendencies, leaks, correlations, recommendations), giving the agent enough to know what comes back. The main gap is behavioral context for an AI compute-backed tool with no annotations, but for a read-only analytics query the definition is close to 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%, so all five parameters (account, account_id, date_from, date_to, market_type) are already fully documented in the schema. The description adds no parameter syntax, format, or interaction details (e.g., account vs account_id precedence), so 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?

States a specific verb and resource ('Get algorithmic and AI-detected pattern observations') and enumerates the output categories (behavioral tendencies, session leaks, duration correlations, recommendations). It explicitly distinguishes itself from siblings by name (get_edge_by_direction, get_edge_by_market), so an agent can tell what this tool returns vs adjacent analytics tools.

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 an explicit 'Best for' list and a 'NOT for' clause that names the two alternative tools for the excluded use cases. The decision boundary between qualitative AI coaching insights and raw numeric edge breakdowns is unambiguous.

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