Edit

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

With no annotations provided, the description carries full burden and delivers substantial behavioral information. It explains execution behavior (sequential processing, stops on first error), preview capability (dryRun returns unified diff), operational constraints (max 50 operations), and matching behavior (fuzzy matching for AST ops). It also clarifies that batch mode stops on first error, which is critical for understanding failure behavior. The description doesn't mention authentication requirements or rate limits, but covers most essential behavioral aspects.

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 efficiently structured and front-loaded, starting with the core purpose ('Edit notes'), then immediately explaining the two operational modes, followed by specific operation types and their semantics, and ending with the dryRun feature. Every sentence adds essential information with zero wasted words. The information density is high while remaining readable.

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?

Given the tool's complexity (12 parameters, two operational modes, multiple operation types) and absence of both annotations and output schema, the description does an excellent job covering essential context. It explains modes, operations, constraints, and preview functionality. However, it doesn't describe the return format (only mentions 'unified diff' for dryRun) or error handling beyond 'stops on first error', which leaves some gaps for a tool with this level of complexity.

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?

With only 42% schema description coverage (most parameters lack descriptions in the schema), the description adds significant value by explaining parameter semantics. It clarifies that path/operation/content are required for single mode, operations array is for batch mode, and explains what different operation types do (AST ops target headings/block IDs with fuzzy matching, freeform ops for line range/literal string, frontmatter_set merges YAML). However, it doesn't explain all 12 parameters individually, leaving some like headingDepth, startLine, endLine, searchText, replaceAll without explicit 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 states the tool's purpose as 'Edit notes' with specific operational modes (single vs batch) and operation types (AST ops, freeform ops, frontmatter_set). It distinguishes itself from sibling tools like 'view' (read-only) and 'vault' (storage management) by focusing on modification operations. However, it doesn't explicitly contrast with 'workflow' which might also involve editing.

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 provides clear usage context by explaining two distinct modes (single vs batch), specifying when to use each (single mode requires path/operation/content; batch mode uses operations array), and mentioning constraints like 'max 50 operations' and 'stops on first error'. It also explains when to use dryRun for previewing changes. However, it doesn't explicitly state when NOT to use this tool versus alternatives like 'system' or 'workflow'.

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