validate_wireframe

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

With no annotations provided, the description carries the full burden and does so thoroughly. It explicitly declares the tool is READ-ONLY, lists what geometry issues are detected, and explicitly states no fixes are applied. It also reveals the underlying shared geometry checker behavior across both reader types, providing context beyond simple annotations.

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 well-organized: it front-loads 'READ-ONLY layout lint' and 'no fixes applied', then efficiently lists checks using parenthetical and slash-separated items. The session type explanation adds a necessary but slightly lengthy second sentence; overall every clause earns its place, though it could be broken into bullet points for even faster scanning.

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?

Despite having no output schema, the description clearly implies the output (violation categories and associated fixer names) and fully explains input types and page-scoping. It gives the agent all necessary information to decide when and how to invoke this tool, covering both usage scenarios and the relationship to fixers. The description is effectively self-contained for this tool's complexity.

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 100%, so the base requirement is met. The description adds meaningful nuance by explaining that reportSessionId can be a legacy ID from open_report or a pbirSessionId from read_pbir, and clarifies that the same checker runs for either, which is not derivable from the schema alone. This goes beyond just repeating parameter descriptions.

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 opens with 'READ-ONLY layout lint' and specifies the resource: 'visual positions + page size'. It then enumerates concrete checks (OVERLAP pairs, OFF-CANVAS, tiny/zero-size visuals, z-order anomalies, margin/gap statistics), clearly distinguishing it from the sibling fixer tools which it explicitly names (auto_arrange, align_visuals, etc.).

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 explicitly states this is a read-only lint with 'no fixes applied' and that 'Every violation names the existing fixer tool', directly guiding the agent to run this before using a fixer like auto_arrange or move_visual. It also clarifies two supported input modes (legacy reportSessionId vs PBIR pbirSessionId) and that the same checker works for both, removing ambiguity about when each session type is valid.

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