AroFlo MCP

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

Annotations establish read-only/idempotent safety; the description adds value by disclosing the client-side filtering behavior, the join operation ('tasks joined with project + tasktotals'), and the grouping/calculation logic ('group tasks by project with total hours'). It also mentions auto-pagination with caps, though doesn't specify cap behavior or rate limiting implications. Could better explain performance characteristics given the client-side processing.

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 achieve brevity but sacrifice necessary documentation given the complexity (12 parameters, 0% schema coverage). The front-loading of core functionality is good, however the density leaves too many parameters undocumented. 'Uses client-side filtering by projectId' is slightly awkward phrasing given projectIds is required, not optional.

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?

Despite having an output schema (reducing description burden), the tool has significant complexity—joining multiple data sources, client-side filtering, pagination logic, and 12 undocumented parameters. The description omits: date filter semantics (which date field each filters), boolean flag purposes (hoursOnly, includeUnassigned), mode enum behaviors, and error conditions. Given zero schema descriptions, the description should comprehensively document parameter semantics but fails to.

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?

With 0% schema coverage across 12 parameters, the description inadequately compensates. While it implicitly references projectIds and pagination controls ('caps'), critical parameters like 'sinceDateRequested' vs 'sinceCreatedUtc' (ambiguous naming), 'hoursOnly', 'includeUnassigned', and the 'mode' enum values lack any semantic explanation. The relationship between 'mode', 'verbose', and 'debug' flags is unexplained despite potential overlaps.

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?

Clearly states the core operation: fetching tasks joined with project/tasktotals data and grouping by project with aggregated hours. Uses specific verbs (fetch, group) and identifies the resource. However, it does not distinguish from sibling 'aroflo_report_open_projects_with_task_hours' which appears to have similar domain overlap, leaving ambiguity about which tool to use for reporting needs.

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?

Mentions 'client-side filtering' which hints at implementation characteristics, but provides no explicit guidance on when to use this tool versus 'aroflo_get_tasks' or the reporting siblings. No prerequisites, error conditions, or 'when not to use' guidance is provided. The pagination mention is technical rather than prescriptive.

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