app.file_new

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

No annotations are provided, so the description carries the full burden. It discloses that force is required when dirty, hinting at behavior (operation may fail without force), but does not fully explain what happens to the current file (e.g., discarding unsaved changes) or the overall state transition. This is minimal behavioral context.

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 sentence, efficient and front-loaded. However, it could be clearer: 'force is required if current file is dirty' might be interpreted as the parameter must be present rather than set to true. Slight ambiguity prevents a perfect score.

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 simple tool with one parameter and no output schema, the description is mostly adequate. It provides the core action and parameter guidance, but lacks details on the state change (e.g., closing current file, creating blank file). Additional context about the workflow 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 coverage is 0% with only a title for the force parameter. The description adds meaning by explaining when force is required (if dirty), which provides semantic context beyond the schema's default and title. This significantly helps the agent understand the parameter's purpose.

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 starts a new empty file. The verb 'start' and resource 'new empty file' are specific. However, it does not distinguish from sibling tools like app.file_open or app.file_save_as, but the purpose is clear enough.

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 implies usage context by stating 'force is required if current file is dirty', but does not explicitly state when to use this tool versus alternatives like saving as a new file. The guideline for the force parameter is present but no alternative comparisons.

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