Recent Changes

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

With no annotations, the description carries the behavioral disclosure burden. It explicitly states the result is paged, ordered newest-first, audited, and includes per-kind counts for the whole log. This goes beyond the schema and gives an agent a solid sense of what to expect, though it does not detail authentication or read-only guarantees.

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?

Two tightly written sentences. The first sentence front-loads the core purpose, ordering, and paging; the second adds return-shape context. There is no filler or redundant restating of the tool name.

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 simple paginated read tool with an output schema, the description covers the essential behavioral context: scope, order, paging, and result shape. It is slightly vague about what 'capture changes' means and relies on the reader knowing the per-note history shape, but the output schema reduces the need for more detail.

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 no descriptions for limit or offset, and the description only indirectly addresses them via the word 'paged.' Limit and offset are standard pagination terms, and the defaults in the schema help, but the description does not add explicit detail about how pagination behaves or what each parameter controls.

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 the resource as 'latest audited vault and capture changes' and provides ordering and pagination context. It does not use an explicit active verb like 'list' or 'get', but the passive 'Returned with...' makes the retrieval intent clear. It also distinguishes itself from per-note history by emphasizing the whole log.

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?

Usage context is implied: this is for recent changes across the entire vault and capture log, contrasted with 'the per-note history reports for one file.' However, it does not explicitly say when to choose this tool over note_history or other sibling tools, and it offers no exclusionary guidance.

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