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

The annotations already cover read-only and closed-world safety, and the description adds value on top: default ordering, the id-per-row shape, cursor-based pagination via next_cursor, and the 30-day window on trash. The one soft spot is "newest first" against a sort parameter that defaults to "updated" — close enough not to contradict, but it leaves the ordering slightly ambiguous.

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 first sentence front-loads purpose and capability in one breath; the no-filter framing and pagination/trash notes follow in a sensible order. The filter enumeration runs long, but it is dense with specifics rather than padding, so it earns most of its length.

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 14-parameter read tool with no output schema, the description covers what an agent most needs: how pages continue, that rows carry ids for read_note, and how trash mode differs. It is thin on return shape beyond the id, but with full schema documentation and the no-output-schema allowance this is close to complete.

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 coverage is 100%, so every parameter, enum and bound is already documented in the schema itself. The description mostly re-enumerates filter categories rather than adding semantics, and its genuinely useful additions (filters compose freely, no-filter behavior, trash/restore lifecycle) are modest. Baseline 3 is the right landing point when the schema carries the weight.

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 opens with a specific verb and resource ("Browse the user's entries") and enumerates the dimensions it can filter on, which maps directly onto the schema. It also routes onward to read_note and restore_note. It stops short of naming search_notes or list_todos, both siblings whose territory overlaps with the text filter and the done/kind filter, so the agent must infer the boundary on its own.

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?

"With no filters it is 'what have I captured lately'" gives a concrete default-use picture, and the trash branch explicitly points at restore_note as the follow-up action. What's missing is an exclusion: nothing states when to page through this list versus reaching for search_notes, even though the free-text filter makes that a live choice.

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