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

The description adds rich behavioral detail beyond annotations: it specifies operation on a throwaway copy, lists exactly what steps return (screens, console errors, data changes, screenshots), enumerates supported step actions with syntax, and confirms nothing is written back. Annotations cover safety, but the description explains the interactive simulation behavior fully.

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 dense but front-loads the core output then details steps, with no wasted sentences. The step examples are compact and informative, though the long parenthetical could be slightly more structured for readability.

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 no output schema, the description fully specifies return content and step behavior. Combined with annotations and a 75%-covered schema, it provides all necessary context for an agent to call the tool correctly, including safety implications.

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 75%, so baseline is lower, but the description compensates by defining step syntax and semantics (e.g., tap, type, scroll) and clarifying that steps act on a throwaway copy. It adds meaning beyond the schema's high-level parameter descriptions, though some details like step limit (30) are in schema, not description.

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 it produces screenshots of a note's app at specified sizes/themes with diagnostics, and optionally drives the UI via a steps array. It's specific about the resource (app/note) and outputs, but doesn't distinguish itself from siblings like fetch, search, or history beyond the screenshot focus.

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?

Usage is implied by listing modes (screenshot mode vs. steps mode) and by the schema field 'on a throwaway copy', but there's no explicit guidance on when to choose this over alternatives or prerequisites for using steps. An agent must infer context.

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