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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description reinforces this by stating 'Read-only; the tool writes nothing — the host agent performs the code edits, verification, and commit.' This adds context beyond the annotations by clarifying the division of labor between the tool and the host agent. It doesn't describe error cases or side effects, but for a read-only preparation tool the key behavioral trait is well covered.

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 dense paragraph that front-loads the core purpose and read-only guarantee, then gives usage guidance. It's slightly long but every sentence earns its place: purpose, behavior, parameter source, and alternatives are all covered. The structure could be improved with line breaks, but the content is efficient.

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?

For a tool with 10 parameters, no output schema, and no required parameters, the description does a good job of orienting the agent: it explains the phase, the read-only nature, the source of taskId, and the alternatives. However, it doesn't explain what the 'implementation instruction plus the impact-chain commit-message format' looks like or how the many optional parameters affect the output. Since there is no output schema, a bit more detail on the return value would improve completeness.

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%, so the schema already documents all 10 parameters. The description adds value by explaining the key parameter (taskId) with an example and its source ('from the task returned by vdd_get_next_task'), but it doesn't clarify the relationship between the many optional parameters (feature, statement, description, actionItemId, capabilities, artifactFiles, availableTools, researchFindings) or when each is needed. Baseline 3 is appropriate since the schema carries the heavy lifting.

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 states a specific verb ('Prepare'), a specific resource ('one task for implementation'), and the exact phase ('VDD Phase 7b'). It clearly distinguishes itself from siblings by naming vdd_get_next_task and vdd_trace as the read-only inspection alternatives. An agent can tell exactly what this tool does and what it is not.

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 gives explicit when-to-use guidance: 'Run one task at a time, after vdd_get_next_task'. It also names alternatives for read-only inspection ('use vdd_get_next_task or vdd_trace instead') and clarifies that the host agent performs the actual edits, verification, and commit. This is strong routing guidance.

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