Conduit

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

Annotations already cover key behavioral traits (readOnlyHint=false, destructiveHint=false, idempotentHint=false, edge case warnings), so the bar is lower. The description adds value by explaining the return format ('Array of objects... with results and any errors') and the batch processing capability with 'skip_errors', which aren't fully detailed in annotations. No contradiction with annotations is present.

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 appropriately sized and front-loaded, starting with the core action and key parameters. The second sentence adds useful detail about options, and the return explanation is necessary. However, the return format description could be slightly more concise, and the structure is straightforward but not optimally segmented.

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 the tool's complexity (batch operations, error handling) and rich annotations (edge case warnings, usage examples), the description is fairly complete. It covers the main functionality, parameter options, and return format. Without an output schema, the return explanation is valuable. However, it could better integrate with annotations to avoid redundancy and provide more context on sibling differentiation.

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 67%, providing good documentation for parameters like 'reorder', 'reorders', and 'options'. The description adds marginal value by clarifying the choice between single config ('reorder') or array ('reorders') and mentioning 'skip_errors', but doesn't elaborate on parameter meanings beyond what the schema describes (e.g., what 'direction' values imply in context). Baseline 3 is appropriate given the schema's 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 clearly states the verb ('reorders') and resource ('one or more nodes in their parents' children arrays'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'move_node' or 'resize_node', which might also affect node positioning. The title annotation 'Reorder Nodes' reinforces but doesn't add differentiation.

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 implies usage for reordering nodes within parent arrays, and annotations provide extra context ('useful for changing stacking order of layers'), but it lacks explicit guidance on when to use this tool versus alternatives like 'move_node' (which might handle spatial movement) or 'set_node_prop' (which could modify properties). The edge case warnings hint at prerequisites (valid parent, children array) but don't frame them as usage rules.

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