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

Annotations already declare readOnlyHint and non-destructive, but the description adds valuable behavior context: what state is returned and the reconciliation/idempotency semantics that govern recovery after ambiguous apply outcomes. It does not cover error cases such as a missing or expired plan ID, but for a read-only query tool the disclosure is rich.

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 tightly packed sentences with no filler; the read-only scope and return contents come first, and the recovery guidance follows. Every clause earns its place.

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?

The tool is simple (one required param, output schema exists) and the description covers what an agent needs: that it is a safe read, what it returns, and exactly when to use it versus retrying apply or creating a new plan.

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 coverage is 100%, so the planId parameter is already fully documented in the schema, and the description adds only the reinforcement that it must be 'this exact plan' rather than a newly created one. Baseline 3 is appropriate when the schema carries the parameter detail.

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 (Gets) and resource (a workflow plan) and explicitly declares it is non-modifying, which differentiates it from the apply/cancel/confirm siblings. It also enumerates what the returned state includes (expiry state, execution status, item errors, diagnostics, old/new values), so the agent knows exactly what it retrieves.

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?

Gives an explicit triggering scenario ('After a timeout or disconnected apply call') and names the two correct recovery paths: query this exact plan or retry apply with the same idempotency key. It also states a hard prohibition: never create a replacement plan until the outcome is terminal and INDETERMINATE items are reconciled.

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