workflowy

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

Annotations indicate destructiveHint=true, readOnlyHint=false, openWorldHint=true, and idempotentHint=false. The description doesn't contradict these (ranking is non-destructive to data, but annotations suggest otherwise—potential contradiction noted below). It adds context about ranking nodes by children count, but doesn't explain what 'destructive' means here (e.g., modifies output format?) or address open-world/idempotent implications. With annotations, the bar is lower, but more behavioral detail would help.

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 description is a single, efficient sentence: 'Rank nodes by immediate children count.' It's front-loaded with the core action and metric, with zero wasted words. Every part earns its place by specifying the operation and scope.

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?

Given 3 parameters, 100% schema coverage, annotations, no output schema, and sibling tools, the description is minimal but functional. It states the purpose but lacks context on output format (e.g., list of nodes with counts?), behavioral nuances from annotations, or integration with siblings. For a ranking tool with destructive annotations, more completeness would aid the agent.

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%, with clear descriptions for item_id (Workflowy item ID, None for root), preserve_tags (preserve HTML tags in output), and top_n (number of top results). The description adds no parameter semantics beyond the schema, such as explaining how 'immediate children' relates to item_id or what 'rank' entails. Baseline 3 is appropriate given high schema coverage.

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 'Rank nodes by immediate children count' clearly states the verb (rank) and resource (nodes) with a specific metric (immediate children count). It distinguishes from siblings like workflowy_report_count (which might count total nodes) and workflowy_report_created/modified (which rank by time), but doesn't explicitly differentiate from workflowy_get/list/search which retrieve rather than rank.

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 description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a Workflowy item ID), exclusions, or comparisons to siblings like workflowy_report_count (which might provide different metrics) or workflowy_targets (purpose unclear). Usage is implied only by the tool name and description.

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