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

With no annotations provided, the description carries the full burden. It explains the meaning of each screenshot kind: 'recorded' (captured during recording), 'live' (what the device showed during replay), and 'diff' (visual diff overlay). It also discloses that the output is a directly viewable image. It does not mention error behavior or side effects, but for a read-only image fetch this is adequate.

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 sentences, zero fluff. The action is front-loaded, the kind options are clearly enumerated, and the usage caution is appended without redundancy. Every sentence earns its place.

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 simple read-only tool with 3 required parameters and no output schema, the description covers purpose, parameter semantics, and usage. It could mention output format details or error cases, but 'as an image you can view directly' is sufficient for an agent to invoke and interpret the result. The absence of annotations is mitigated by the explicit kind explanations.

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 baseline is 3. The description adds meaningful semantic value for the 'kind' parameter by explaining exactly what 'recorded', 'live', and 'diff' mean, going beyond the schema's terse 'Which image to load'. It also reinforces the 1-based stepIndex, though that is already in 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?

The description clearly states the action: 'Return the screenshot for one step of a replay as an image you can view directly.' It specifies the resource (replay step screenshot) and the outcome (a viewable image). This distinguishes it from siblings like flow_replay_step, which likely returns step data rather than screenshots. The three kind values are also explained succinctly.

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 offers a usage hint: 'Use selectively — not every step needs visual inspection.' This implies when to use the tool but does not explicitly name alternatives or state conditions for choosing another tool (e.g., flow_replay_step for text details). The guidance is present but thin.

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