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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: locked notes are skipped and counted in locked_skipped, Recently Deleted is never searched, snippets are match-context, and it warns that note content is untrusted data rather than instructions.

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?

Front-loads scope and safety in the first clause, then walks through each parameter in order, then return shape, then exclusions. Dense but every sentence adds operational information.

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?

Covers behavioral edge cases (locked notes, Recently Deleted), and even summarizes result fields (id, title, folder, account, dates, snippet) so an agent needn't consult the output schema for the essentials. Complete for a filtered search tool.

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 0% schema coverage the description must carry the load, and it explains query (title + full body, case-insensitive), folder (name or path fragment, with a 'Work/Clients' example), and since (ISO date or unix seconds). Only limit is left unexplained.

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?

Names a specific verb and resource with scope: 'Search Apple Notes on this Mac', plus the default ordering ('newest first by last change'). This clearly separates it from get_note (full-text read) and from search_mail/search_contacts siblings.

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?

Explains the two main modes (with a query vs. no query listing recent notes) and routes to the sibling 'read the full text with get_note'. It gives condition-based routing but no explicit when-not-to-use guidance.

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