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

Annotations already cover the read-only/idempotent profile, yet the description adds non-obvious behavioral context: generic containers are excluded from context sizing unless component is empty, values are captured CSS rather than inferred tokens, and returned IDs live in the raw capture idSpace rather than the enriched MCP layers. These caveats are exactly what an agent could otherwise get wrong when interpreting or joining results.

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?

Front-loaded with the purpose, then compact sentences covering mode, exclusions, value provenance, ID space and pagination; every sentence carries load. It is dense with clauses and semicolons in a way that borders on cramped, which keeps it just under the top mark.

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 nine-parameter tool with an output schema and annotations, the description covers the behavioral gaps an agent needs: result shape in default vs summary mode, pagination, exclusion rule and ID-space caveats. Version/environment pinning and other parameter mechanics are already fully covered by the schema, so little is missing.

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 100%, so the baseline is 3, but the description goes beyond it by explaining the mode switch of summary (aggregate value matrix, generic elements included when component is empty) and the hasMore/offset pagination contract. It adds meaning rather than repeating the schema.

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 specific verb+resource: observed width/height/min-max dimensions for one page/view, grouped by semantic component kind. That scope is distinctive against nearby siblings like get_spacing, get_component_styles and get_component_typography, so an agent can distinguish it without opening the schema.

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?

Gives real usage steering: default vs summary=true mode (aggregate matrix, includes generic elements when component is empty), how to page via hasMore/offset, and to use find_elements by label to resolve layer IDs. It stops short of saying when to prefer this over sibling measurement tools, so it is clear context rather than full when/when-not routing.

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