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

Discloses the frame selection algorithm (explicit evidence, closest at/after timestamp with earlier fallback), the behavior of `window` (neighbouring candidates), and that signed URLs are short-lived and may be null. This is consistent with the read-only and idempotent hints.

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?

The description is detailed but each sentence contributes essential information about selection, fallback, and parameter effects. It is slightly longer than necessary but remains focused and free of extraneous content.

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?

While there is no output schema, the description explains the return format (representative frames per step, candidates, signed URLs) and the conditions under which URLs may be null. This is sufficient for an agent to understand the result, though a formal output schema would add more precision.

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?

All five parameters are covered in the schema and the description adds meaningful semantics: `window` explains neighbouring frames and candidates, `size` explains full vs thumbnail, `step_ids` explains comma-separated resolution, and `process_id`/`snapshot_id` are clearly identified. The description enhances the schema rather than merely repeating it.

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 tool returns one representative screenshare frame per current-process step, with explicit selection logic. It distinguishes itself from other list tools by focusing on step frames and their resolution.

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?

Provides concrete guidance on when to use the `window` and `size` parameters, and explains the fallback behavior when the selected frame does not show the step. While it does not explicitly compare to sibling tools, the context and parameter instructions are sufficient for usage.

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