conduyt_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 disclosure burden. It partially meets it by describing the shape of results per query type ('rows, total, metric, chart data, pivot'), which is genuinely useful. It never states that the tool is read-only, what permissions/API-key scope it needs (only hinted via 'this key can run'), or whether large reports are bounded — gaps that matter for a no-annotation tool.

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 purpose is front-loaded in the first sentence and the enum enumeration follows, so the agent can stop reading once it finds its query type. The second sentence is a dense ~150-word run-on, but given 11 distinct query types there is little fat — each parenthetical carries real disambiguating content.

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 tool with 11 modes, nested objects, and no output schema or annotations, the description does substantial work: every query type is named with its output content, and windowing/paging behavior is called out. Remaining gaps are the read-only/safety profile and error behavior (the 409 on ambiguous report names lives only in the schema), which keep it from a 5.

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%, so all six parameters including nested report/dashboard/filters objects are already documented in the schema. The description reinforces the mapping (period/dateRange for saved_report and dashboard, page/perPage for saved_report, reps and sources) but largely restates what the schema's per-property descriptions already say. 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 ('Query') and resource ('AI-powered CRM insights') and then enumerates all 11 query types with parenthetical detail on what each returns. The purpose is unambiguous. It stops short of differentiating itself from overlapping siblings such as conduyt_run_report and conduyt_run_dashboard, so an agent cannot tell which tool to prefer when both could answer a 'run this saved report' request.

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?

Usage is implied by the query-type list — the agent can infer which enum value handles 'stale deals' or 'open/click rates' — and it names the optional windowing/paging for saved_report. But there is no explicit when-to-use-this-vs-alternative guidance despite heavy sibling overlap (conduyt_run_report, conduyt_run_dashboard, conduyt_agent_performance_report, conduyt_ai_deal_insights), and no exclusions or prerequisites.

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