Extract a specific frame from a recording session by index and save it as a PNG for inspection or analysis; optionally choose the session folder, or use the last recording.
Get a specific frame from a recording session. Saves as PNG file.
| Name | Required | Description | Default |
|---|---|---|---|
| frame_index | No | The frame's number, from 0 | |
| session_dir | No | The session's folder; the last recording when empty |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.2.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds one useful behavioral fact not in the annotations — the frame is materialized as a PNG file — but it omits where that file lands, whether it is returned as a path, and whether repeated calls overwrite the same artifact. There is mild tension between "Saves as PNG file" and readOnlyHint, though it reads as a non-mutating export rather than a contradiction.
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 short sentences, front-loaded with the core action, with no filler. The second sentence is slightly orphaned because it states a file is saved without saying where, but nothing is wasted.
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 two-parameter read tool with an output schema and full annotation coverage, the description is adequate to call it. It stops short of telling the agent what the PNG side effect means practically — output location, overwrite behavior, or dependence on an active/stopped recording — which matters given the sibling recording tools.
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 both frame_index (0-based) and session_dir (empty means last recording) are already fully documented in the schema. The description adds only the notion of a "recording session" that frames belong to, which does not go beyond the schema's own wording. Baseline 3 applies.
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?
"Get a specific frame from a recording session" gives a concrete verb and resource, and the second sentence clarifies the output form (PNG). It is distinguishable from mutating siblings like start_recording/stop_recording, but it never contrasts itself with the other capture-style sibling (capture_viewport), leaving a small ambiguity about which screenshot-like tool to pick.
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 phrase "from a recording session" implies the precondition (a session must exist), but there is no explicit when-to-use statement, no mention of start_recording/stop_recording as prerequisites, and no exclusion of the alternative capture_viewport. Usage is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.