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

The annotations already declare readOnly and idempotent behavior, so the bar is lower. The description adds meaningful behavioral detail beyond the annotations: results are ordered 'newest first', and 'private notes are searched too', clarifying the query scope.

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 short sentences with the primary action front-loaded ('Find your saved reading by text or kind'). Every clause carries information—filtering, ordering, and query scope—with no filler.

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 tool is simple with four optional parameters, and the description covers its core behavior adequately. However, with no output schema, it omits useful context such as the response shape, whether query and kind combine via AND, and how limit/offset interact with the newest-first ordering.

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 description coverage is 100%, so the baseline is 3. The tool description adds a default sort order ('newest first') and reinforces that queries span private notes, which are behavioral details not fully captured in individual parameter descriptions.

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 states a specific action ('Find') on a specific resource ('saved reading'), and the title 'Browse bookmarks' reinforces a list/search operation. It clearly distinguishes from sibling tools like bookmarks_add, bookmarks_delete, and bookmarks_get by emphasizing text/kind filtering and newest-first ordering.

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 implies a search/browse use case ('Find your saved reading by text or kind'), and sibling tool names suggest bookmarks_get handles individual retrieval. However, it never explicitly states when to prefer this over bookmarks_get or archive_search, leaving the boundary to inference.

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