Extract a visual contract

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

Annotations declare readOnlyHint=false and openWorldHint=true; the description is consistent with that, disclosing the file write to outputPath, the optional screenshot capture, and the shape of the returned summary (element count per viewport, warnings, written path). It stops short of permissions, overwrite behavior, or runtime cost for a browser-driven extraction, which is the remaining gap.

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?

Four sentences, front-loaded with the action and side effect before the workflow constraints. Every sentence contributes routing or dependency information; only the return-summary sentence could arguably be trimmed if an output schema existed.

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 13-parameter, no-output-schema tool, the description covers purpose, ordering relative to all three siblings, the downstream screenshot dependency, and the return summary. What remains thin is handling of the many extraction-tuning parameters, though the schema documents them fully.

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 adds workflow meaning beyond the schema for two parameters: outputPath is where the contract JSON lands, and screenshotDir is a downstream dependency for diff_pixels rather than merely a directory. The other eleven parameters are only covered by 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 and resource ('Extracts a visual contract from a reference URL') plus the persistence side effect ('saves it as JSON at outputPath'). It names the siblings it precedes (check_implementation, diff_pixels), so an agent can place it in the workflow without opening any 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?

Explicit ordering rule: 'Call this once per reference design, before check_implementation or diff_pixels can be used.' It also gives conditional guidance for a specific parameter ('Pass screenshotDir to also capture reference screenshots, which diff_pixels requires later'), which is exactly the when/when-not information an agent needs.

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