search_browser_roots

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld). The description adds genuinely new behavior: unavailable roots are surfaced, results report exact root/path identity, and truncation is explicit for both result limits and scan limits, plus the join rule for private MCP tags/favorites (exact URI required). That is substantive context beyond the annotations.

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 dense sentences, with the core action and result shape front-loaded before the disambiguation clause. Some jargon ('exact root/path identities', 'scan-limit truncation') costs a little readability but no sentence is wasted.

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?

No output schema exists, and the description does describe the return composition (identities, unavailable roots, truncation flags) and the conditional tag/favorite join, so an agent knows what to expect. The main residual gap is the absence of routing guidance against sibling browser tools.

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 67%, so the schema documents most parameters itself. The description adds little for limit/maxDepth/maxVisited beyond the truncation note, and its includeMetadata phrasing largely restates the schema's own wording. Marginal value over the structured fields, so baseline 3.

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?

States a specific verb+resource ('Search ... Live browser roots') and enumerates what the result carries (exact root/path identities, unavailable roots, truncation). It also carves out a negative boundary ('not a native Live collection or Splice cloud search'). However, it never names its closest siblings (list_browser_roots, search_browser_items), so the agent must infer which root/item tool applies.

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?

Implies usage via 'selected or all available Live browser roots in order' and the optional MCP tags/favorites join, which tells the agent this searches roots rather than items. But there is no explicit when-to-use / when-not-to-use statement or named alternative, only the negative Splice/collection caveat.

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