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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: singular currency of the step ('the first step not closed in the open phase') and the empty-return case when a phase is complete pending user validation. It does not cover error behavior for an invalid or inactive plan_id.

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?

Front-loaded with the core verb and returned payload, then two sentences that each handle a distinct edge case (step singularity, phase-complete emptiness). The long enumeration is dense but every item earns its place because there is no output schema to document the return shape.

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 no output schema, the description must describe the return payload, and it does so item by item. Combined with the phase-complete empty-result rule, an agent has enough to call this correctly and interpret the response, including the null case.

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 sole parameter plan_id has 0% schema description coverage, so the description must carry the meaning. It only implies that plan_id references an 'active plan' — it does not say whether a closed, unknown, or non-active plan_id errors or returns empty. Minimal added meaning over the bare string schema.

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 and resource ('Returns the working frame of the current step of an active plan') and then enumerates exactly what that frame contains: goal, phase/step numbers, instruction, done-criteria checklist, expected deliverable, prior deliverables, and rule. This enumeration distinguishes it from siblings like plan_list or plan_status, which would not return the step-level working frame.

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 definition makes the triggering condition clear: call it to learn what the active step is, and the 'only one step is current at a time' sentence defines which step that will be. It also tells the agent what an empty result means ('no step is returned until the user validates the phase'), implicitly routing to plan_validate, though it never names an alternative tool or an explicit when-not-to-use condition.

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