list_notes

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

In addition to the annotations (read-only, idempotent, non-destructive), the description adds meaningful behavior: ordering of results, preview semantics, an explicit explanation of the substring behavior, and clarity about total_count exceeding returned results when limit truncates the page. This is exactly the kind of behavioral context the description should provide.

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 three concise paragraphs with a front-loaded summary, a filter guidance section, and a brief output-shape section. Every sentence contributes necessary behavioral or usage detail, and the structure makes it easy for an agent to parse.

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 description covers the core operation, ordering, filtering behavior, returned entry fields, total_count semantics, and limit-pagination behavior. Combined with a rich output schema and the read-only annotations, virtually everything an agent needs to invoke this tool correctly and interpret the default behavior is present.

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 input schema already covers both parameters thoroughly: limit defines maximum notes with defaults and bounds, query explains the case-insensitive substring filter and omission. The description restates some of this guidance but does not add significant new meaning for the parameters; its advice about using one distinctive word is minor beyond the schema's coverage.

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 a specific action ('List notes') and a distinctive resource, and also specifies the ordering (most-recently-updated first) and output shape (previews), which precisely distinguishes it from the single-record sibling get_note. It doesn't explicitly call out the sibling, but listing versus retrieving a single note is semantically self-evident.

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 gives concrete usage guidance for the query filter: it explains that the filter matches case-insensitive substrings, warns that it is not fuzzy or semantic, and counsels preferring one distinctive word over a phrase. It also says to omit the filter to browse everything, but it doesn't explicitly contrast list_notes with get_note for retrieving a single full note.

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