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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds the non-obvious payload-weight warning and discloses that both recorded and live XML are returned, which is real behavioral context. It does not discuss cost limits or failure modes for invalid ids.

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?

Two sentences, zero waste: the payload contents are front-loaded and the heaviness caveat lands last where it most affects the call decision. The field list is dense but every item is information an agent needs to decide whether to call it.

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?

With no output schema, the description usefully enumerates the return shape and the cost of calling it, which is what an agent needs here. Minor gap: no guidance on behavior when replayId or stepIndex is invalid/out of range.

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% and both params are already documented, so the schema does the heavy lifting. The description only reinforces that stepIndex selects a single step of a replay; the note that it comes from flow_replay_summary 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?

States a specific verb+resource ('Full data for ONE step of a replay') and enumerates exactly what is returned: action type, recorded element/locators/coordinates, both page-source XMLs, locator used, scores, error. The uppercase 'ONE' distinguishes it from flow_replay_summary, which covers all steps.

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?

'Heavy — call selectively for steps you want to diagnose' gives a clear selection condition (targeted diagnosis rather than bulk retrieval), implicitly routing overview needs to flow_replay_summary. It stops short of naming that sibling or stating explicit when-not-to-use conditions.

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