node_snapshot

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

With no annotations provided, the description carries the full behavioral burden and does meaningful work: it discloses that output files are 'never overwrites', that 'yaml' is 'default, token-cheap', and that 'summary' truncates long lists to '25 + count'. The only notable omissions are an explicit statement that the tool is read-only with respect to the node and the exact mechanism of the diff.

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 opening line is front-loaded and information-dense, and the parameter documentation is organized into a compact per-line structure. Every sentence earns its place, though the inline parameter docs add mild density that could be considered schema material.

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 no annotations and no output schema, the description covers purpose, all parameters, output detail levels, and file behavior well. However, the 'diff two snapshots' workflow is underspecified — there is no diff parameter or description of what the diff output looks like — and the return value shape is left to inference despite the absence of an output schema.

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 0%, so the description must compensate, and it does: each parameter receives meaning beyond the bare type — path is the 'Operator path', out is a 'JSON file under the project folder', detail enumerates full/summary/minimal with truncation behavior, and response_format explains yaml/json with the token-cost tradeoff. This is strong compensation; only path is terse, so it is not a 5.

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 states a specific resource ('Complete parameter state (value/mode/expr/evalError) + flags') and an operation (snapshot/diff), with the 'optionally written to a JSON file' behavior. It is clear what this tool does, but it does not explicitly differentiate itself from closely named siblings such as project_snapshot, bridge_snapshot, or par_get_all, so it stops short of a 5.

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 'Diff two snapshots around a risky edit' provides a clear workflow context for when to use the tool — capture state before and after a risky modification. It offers clear context but no explicit exclusions or alternative-tool routing, matching the 'clear context, no exclusions' level.

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