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

The description discloses non-obvious side effects: resetting the draft to pending, invalidating the cached render, and tier-specific daily rate caps. These details go well beyond the sparse annotations and help the agent predict what invoking the tool will change.

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?

One dense, front-loaded sentence states the action, the optional steering, and the important side effects. The follow-up sentence adds rate limits with no filler or redundancy.

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 description covers the essential behavioral context an agent needs before calling the tool, and the schema handles the strict context/prompt requirements. It does not describe return values, but there is no output schema and the return format is not necessary for correct invocation.

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 description adds meaning beyond the schema by clarifying that draft_id refers to one draft's story text and that angle steers the re-draft. It does not mention handle or context, but the schema already documents those in detail, including the strict context word-count requirements.

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 precise operation: re-drafting one draft's story text with an optional angle. This clearly distinguishes it from generate_draft by indicating an existing draft, and also mentions follow-up effects like resetting to pending and invalidating the cached render.

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 behavior implies when to use it, but it never explicitly says 'use this instead of generate_draft for an existing draft' or names alternatives/exclusions. Rate caps give some usage context, but there is no explicit routing among sibling tools.

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