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

Annotations already cover read-only, idempotent, non-destructive, open-world. The description adds genuinely new behavioral context: that CAPTCHA is not solved (a hard limitation), that the image is tied to the revision actually served, and that no entries/messages/payments occur. That is real value beyond the 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?

Four short sentences, front-loaded with the core action and constraint, with no filler. Slightly choppy but each sentence carries information.

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 read-only, two-parameter tool with full annotation coverage and no output schema, the description covers the essential caveats: side-effect profile, CAPTCHA limitation, and revision semantics. It could say more about the returned image format, but nothing critical 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 0%, so the description carries the load. It does explain the viewport enum values ('desktop or mobile') and implies the screenshot is of the promotion identified by promotion_id, but it adds no format, sizing, or identity details beyond that.

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: 'Return a desktop or mobile screenshot of the standard test preview.' The viewport options and 'tied to the revision actually served' scope it further. It does not, however, distinguish itself from the sibling preview_promotion, which an agent must choose between.

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?

'Compare the image against the requested design' implies the review use case, and 'standard test preview' hints at scope. But there is no explicit when-to-use or when-not, and no routing versus preview_promotion or validate_promotion.

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