Query perspectives

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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds useful behavior beyond annotations: custom perspectives require Pro, and the tool returns perspective metadata/filter rules rather than tasks. This is consistent with the readOnlyHint.

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 short, front-loaded with the main purpose, and every sentence contributes: what it lists/reads, the Pro requirement, and the explicit exclusion with an alternative. No filler.

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?

With annotations and an output schema present, the description covers the essential invocation context: scope of the query, Pro requirement, and the task-returning exclusion. The only notable gap is not specifying how to target a custom perspective for the 'get' action, which is modest for this simple read-only tool.

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?

The schema already documents 'action' and 'perspective_name', and description coverage is partial (67%). The description adds conceptual context about built-in vs custom perspectives and filter rules, but it does not clarify how perspective_id vs perspective_name should be used for the 'get' action, especially since no parameters are required.

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 uses specific verbs ('List', 'read') and a clear resource ('perspectives'), then explicitly distinguishes itself from query_tasks by stating it does not return the tasks inside a perspective. This makes the tool's scope easy to identify.

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?

It gives an explicit alternative for the excluded use case: 'use query_tasks with source=custom for that.' It also calls out the OmniFocus Pro requirement for custom perspectives, which is a practical prerequisite an agent needs to know before invoking.

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