Capture a bounded readback snapshot of an open document to inspect its current state, optionally writing the full manifest JSON for verification.
Capture a bounded readback snapshot for an active/opened document, optionally writing the full manifest JSON.
| Name | Required | Description | Default |
|---|---|---|---|
| visible | No | ||
| read_only | No | ||
| model_path | No | ||
| document_id | No | ||
| output_path | No | ||
| include_manifest | No | ||
| close_after_probe | No | ||
| require_active_document | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavior. It indicates a read-like 'readback' operation and an optional manifest write, but it does not mention important side effects or defaults such as close_after_probe=true, require_active_document=true, or whether the document state is affected.
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 a single front-loaded sentence with no filler, and the primary action and scope are stated first. However, the jargon 'bounded readback' and the compressed list of behaviors could be structured more helpfully.
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 tool with 8 parameters, no annotations, no output schema, and no per-parameter descriptions, the one-line description is insufficiently complete. It lacks information about return values, side effects, default behaviors, and how this tool relates to the many readback/probe/verification siblings.
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?
The schema has 0% description coverage and all 8 parameters are undocumented, so the description must compensate. It only loosely maps to document selection ('active/opened document') and manifest output ('writing the full manifest JSON'), leaving parameters like visible, read_only, model_path, and close_after_probe without meaningful guidance.
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 identifies the action ('Capture') and the resource ('bounded readback snapshot') for an active/opened document, and mentions the optional manifest JSON writing. However, it does not explicitly distinguish this from closely related sibling tools such as probe_document_readback or verify_document_readback_stability.
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 implies usage context by referring to an 'active/opened document' and optional manifest output, but it never states when to prefer this tool over alternatives or when not to use it. There is no explicit routing to any sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.