node_snapshot

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

With no annotations, the description here carries the full burden of behavioral disclosure. It clearly states it captures state, may write to a JSON file, and never overwrites. This communicates a non-destructive side effect and the scope of captured data. Missing details about the return value or failure behavior leave more transparency on the table, but the critical write-safety guarantee is explicit.

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, front-loaded, and provides the key details in 2 sentences, followed by compact inline parameter docs. It contains descriptive statements instead of tautology, though the phrase 'Diff two snapshots around a risky edit' might deserve rephrasing as it is a suggested workflow rather than a tool operation.

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 only 2 parameters and a relatively simple purpose, so the description covers the essential call details. However, there is no description of the returned data (e.g., whether it returns the snapshot, a file path, or confirmation) and the 'Diff two snapshots' wording is not actionable without clear guidance on how two snapshots would be compared. These are notable gaps for an agent needing to use the 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 0%, so the inline parameter notes are essential. 'Operator path' and 'JSON file under the project folder' add meaning that is absent in the input schema. They are concise and enough for an agent to know what to provide, though they do not explain path format validation or behavior when the file already exists.

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 identifies a specific action: capture the complete parameter state (value/mode/expr/evalError) plus flags, with an optional JSON file output. It distinguishes itself from sibling node read tools like node_get by emphasizing full state and flags, but the phrase 'Diff two snapshots' introduces ambiguity about whether this tool actually performs a diff or simply supports a diff workflow.

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?

There is a clear suggested context: 'Diff two snapshots around a risky edit.' However, the description does not explicitly state alternatives or provide exclusions, so an agent is not told when not to use this tool or which sibling tool might be more appropriate for other snapshot-like needs.

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