List the bookmarks inside a Smart View, optionally scoped to one tab/bucket. Use the returned ids with archive_bookmarks / tagging tools to act on the view.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The smart view slug. | |
| limit | No | Page size (1-100). | |
| bucket | No | Which tab/bucket of the view to read (default: all). | |
| cursor | No | Numeric offset for the next page. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, covering safety and side-effects. The description adds the optional bucket scoping and the downstream usage of returned ids, which is helpful but does not deeply explain behavior like return format or pagination. With annotations covering the key traits, a 3 is appropriate.
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 sentences, no filler, front-loaded with the core action and scope. The mention of downstream use is placed second, making the primary purpose immediately clear. Each word contributes to understanding.
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 read-only list tool with no output schema, the description adequately covers the action and optional scope. It omits specifics about return structure or pagination details, but the schema handles pagination parameters (limit, cursor), and annotations cover safety. The hint about using ids closes the loop for task completion, making it nearly complete, but a description of the response shape would push it to 5.
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 all parameters (slug, limit, bucket, cursor) are documented in the schema. The description adds the note about 'optionally scoped to one tab/bucket' and 'returned ids', which slightly reinforces bucket's meaning but adds little beyond the schema. Baseline of 3 holds; no significant added value.
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 verb ('List') and resource ('bookmarks inside a Smart View'), plus an optional scope ('one tab/bucket'). It clearly differentiates from siblings like list_bookmarks and get_smart_view by specifying the view context and mentions using returned ids with other tools, which distinguishes its purpose.
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 clear context for when to use it (to list bookmarks in a smart view) and explicitly states how to use the result ('Use the returned ids with archive_bookmarks / tagging tools to act on the view'). It does not explicitly contrast with alternatives, but its scope is well-defined; the sibling tool names imply alternatives. Lacks explicit when-not guidance, so not a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose, even among similar ones (e.g., archive_bookmarks vs archive_bookmarks_by_filter, get_bookmark vs get_library_overview). Descriptions are detailed and explicitly differentiate between overlapping actions, leaving no ambiguity.
Most tools follow a consistent verb_noun pattern (e.g., list_bookmarks, create_smart_view, update_digest_preference), but a few deviations exist: 'recall', 'remember', 'forget' omit objects, 'get_me' uses a pronoun, and 'setup_vector_store' uses 'setup' instead of 'set'. These are minor and do not hinder readability.
At 53 tools, this far exceeds the recommended 3-15 range and even the 25+ threshold, making it an extreme count. While the server covers a broad domain, the sheer number overwhelms an agent's discovery and selection process, fitting the rubric's definition of an extreme mismatch.
The tool set provides comprehensive lifecycle coverage for bookmarks (fetch, list, get, search, archive, tag), labels (add, remove, delete, list), smart views (create, update, delete, list), digests (compose, send, list, get, preferences), exports, sync status, and user preferences. No obvious gaps or dead ends exist for the stated purpose.
