scene.screenshot

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

Annotations are all false (readOnlyHint=false, openWorldHint=false, idempotentHint=false, destructiveHint=false), so the description carries the burden of behavioral disclosure. It mentions 'Risk: standard; maturity: L1' and 'Per-request argument checks and session policy still apply', which adds some context, but it does not explain what side effects occur (e.g., writes a file to disk, requires a committed snapshot, may fail if the scene is not committed). The description does not contradict annotations, but it leaves the actual behavior vague.

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 short and front-loaded with the command name, but it spends two sentences on generic requirements ('Per-request argument checks and session policy still apply; Approved output root') that are likely boilerplate across many tools. The 'export additionally requires a committed snapshot' is useful but could be more specific. It is not overly verbose, but it does not earn a higher score because the content is mostly generic.

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?

The tool has 7 parameters, no output schema, and annotations that are all false, so the description must compensate. It does not explain the return value (e.g., whether it returns a file path or a success message), the exact file format behavior, or the relationship to the transaction system. The mention of 'committed snapshot' hints at a dependency on `blender_transaction_commit`, but the description is incomplete for an agent to confidently invoke this tool correctly.

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 43%, meaning some parameters (path, width, height) have no descriptions in the schema. The description does not explain these parameters either, so the agent must infer that `path` is the output file path and `width`/`height` are image dimensions. The `_transactionId` and other underscore-prefixed parameters are partially described in the schema. The description adds no parameter-level meaning beyond what the schema provides, so a baseline 3 is appropriate.

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 names the command `scene.screenshot` and mentions 'export additionally requires a committed snapshot', which implies the tool captures a screenshot. However, it never explicitly states the verb+resource (e.g., 'Captures a screenshot of the current Blender scene to a file'), and it does not distinguish this from sibling tools like `blender_preview_capture` or `blender_view_present`. The purpose is inferable but not clearly 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?

The description mentions requirements (approved output root, committed snapshot for export) but does not explain when to use this tool versus alternatives like `blender_preview_capture` or `blender_render_configure`. It gives no context about typical use cases, such as capturing a viewport screenshot for documentation or visual verification. The requirements are stated but the when-to-use guidance is absent.

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