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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds genuine value beyond them: it says the return is a directly viewable image and explains what each kind value represents (captured during recording vs device during replay vs diff overlay), which the schema only labels as 'Which image to load'.

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?

Three tight sentences, front-loaded with the action and return type, then enum semantics, then usage restraint. No filler, though the kind explanation is necessarily a bit dense.

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?

No output schema exists, so the description correctly explains the return ('an image you can view directly'), and the required parameters are fully documented by the schema. Nothing essential for correct invocation 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 baseline is 3. The description earns above baseline by disambiguating the enum values for 'kind' (recorded/live/diff) in terms an agent can reason about, going beyond the schema's terse 'Which image to load'.

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: 'Return the screenshot for one step of a replay as an image you can view directly.' This clearly separates it from step-data siblings like flow_replay_step, though it never names an alternative explicitly, so sibling differentiation is implicit rather than stated.

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?

'Use selectively — not every step needs visual inspection' gives a real restraint signal (when-not to overuse), but there is no explicit when-to-use context, no named alternative (e.g., flow_replay_step for textual step data), and no cost/rate rationale for the selectivity.

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