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

With no annotations, the description carries the full behavioral burden. It implies an authenticated read operation via 'signed-in user,' but discloses nothing about ranking criteria, determinism, item-count limits, latency, or whether any state changes. A reranking tool with zero annotation coverage needs more disclosure than this.

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?

A single front-loaded sentence with no filler or redundancy. It is efficient, though its brevity reflects under-specification rather than deliberate economy.

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 two-parameter reranking primitive with no annotations and no output schema, the description omits the essentials an agent needs: that it operates on a caller-provided candidate list, what ranking signal is used, and how it relates to the sibling search pipeline. The only added context is the signed-in-user scoping.

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 both parameters (query, items with required id/title) are already documented in the schema. The description adds no syntax, format, or semantic detail beyond it; the baseline of 3 applies.

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 gives a specific verb+resource (rerank listings) and hints at personalization via 'signed-in user,' so the action is identifiable. However, it does nothing to distinguish this from the many sibling search tools (search_smart, search_embed, search_parse_intent, search_query_router), and 'rerank' alone doesn't convey that the caller must supply the candidate set.

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 guidance on when to use this versus the sibling search tools, nor any statement that this is a downstream primitive operating on caller-supplied candidates rather than doing retrieval itself. The agent must infer usage entirely from the required 'items' parameter.

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