get_app_insights

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

With no annotations the description carries the full burden, and it does real work: it discloses the 5-minute cache, that the operation may 'generate' insights rather than just read them, and the shape of each returned insight (count, new_count, items). It omits auth requirements, latency/cost of cache misses, and pagination 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?

Purpose, return shape, and filtering are front-loaded in three tight sentences. The Args block partly repeats the prose but is justified given 0% schema coverage, and the parenthetical cache note is worth its tokens.

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?

An output schema exists, so the description is not obligated to explain return values, and it still usefully names the insight categories. What remains unaddressed for a read tool with zero annotations is error behavior on an invalid insight_type and the cost implications of the generate-on-miss path.

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 0%, yet the description documents all three parameters: app_id's meaning (Scout APM application), the enumerated valid insight_type values (n_plus_one, memory_bloat, slow_query) which appear nowhere in the schema, and limit with an effective default of 20. This is exactly the compensation the low coverage requires.

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 or generate all insights for an application') and immediately enumerates what an insight is (N+1 queries, memory bloat, slow queries), which differentiates it from get_app_metrics or get_app_endpoints. It never explicitly contrasts itself with those siblings, keeping it below a 5.

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 'If insight_type is provided, only that type will be returned' line is filter behavior, not guidance on when to pick this tool over get_app_metrics or get_app_anomaly_events. Usage is only implied by the resource name; there are no when/when-not statements or named alternatives.

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