sw_revise

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that overrides affect simulation parameters, while design does not affect simulation parameters but writes into the plan document. This gives important side-effect context beyond the schema.

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 well-organized with a clear intro, code examples, and a clarifying note about design. It is slightly verbose but every sentence adds useful context, and the structure makes it easy to parse.

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?

Given the tool has no annotations and an open-ended overrides object, the description provides enough context to understand the main behavior and side effects. The presence of an output schema means return values don't need to be described. Minor missing details include merge/replace semantics and whether both overrides and design can be provided simultaneously.

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 0%, so the description must compensate. It does well for overrides and design by providing concrete examples and semantics. However, the required draft_id parameter is only shown in examples and not explicitly explained, leaving a small gap for a required parameter.

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 clearly states the tool's purpose: it differentially revises a proposal, requiring only the changes rather than a full restatement. It provides concrete examples of the two main use cases (overrides and design), which distinguishes it from other proposal-related tools like sw_plan or sw_generate.

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 usage context with examples: if the user wants to change simulation parameters, use overrides; if the user wants to record design choices, use design. It also implies when not to use this tool (when you don't need to restate the full requirement), but it does not explicitly name alternative tools or exclusion scenarios.

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