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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuinely new context: one call returns both the saved pages and the active page's last report (batching behavior), and it discloses the auth model - a signed-in account sends X-Organization-Id while a guest gets one temporary workspace. It does not discuss pagination or result ordering, which keeps it off a 5.

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 purpose and the bundling behavior are front-loaded, which is good structure. However, sentences like "The UI groups pages by site in Projects and opens each site in a work tab" and "The introduction stays in Welcome" describe interface presentation rather than agent-relevant behavior and do not earn their place. The description is also repetitive about grouping by site.

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 one-parameter read-only list tool with full schema coverage and clear annotations, the auth context and the note that one call returns both pages and the active report make it largely callable. What is missing is any sense of the return shape - fields per tab, ordering, whether the "last report" can be null - and there is no output schema to compensate. Adequate but with a clear gap for a tool whose main value is the payload it returns.

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% with a single required guest_token whose description already covers the X-Guest-Token header and reuse semantics. The description reinforces this by noting a guest owns one temporary workspace, which clarifies token scope, but adds no format or validation detail beyond the schema. Baseline 3 applies where the schema does the heavy lifting.

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 first sentence gives a concrete verb and resource: "Lists the owner's saved pages (guest or session), with the active page's last report." That distinguishes it from create_tab and run_tab in the sibling list. It loses a point because it never actually uses the word "tab" that the tool name advertises, and jargon like "saved pages" and "last report" leaves the resource slightly ambiguous.

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?

There is no statement of when to call this versus list_sites, get_site, tab_history, or create_tab. The description explains output shape and grouping conventions but never gives a selection condition or prerequisite beyond the implicit "you need tabs." An agent must infer the trigger from the tool name alone.

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