Render the results

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, and the description adds genuinely new traits beyond them: graceful degradation when the host has no UI support, a hard prohibition on inventing URLs or factual titles, and the note that this does not consume search credits. These are behavioral facts an agent could not derive from the annotations or schema.

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?

Four tight sentences that are front-loaded: capability and fallback first, then when to use, then input constraints, then explicit non-capabilities. No sentence is redundant with structured fields, and each adds a distinct constraint.

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?

An output schema exists, so return values need no prose explanation. The description still covers everything an agent needs to invoke it correctly: caller prerequisites, ordering intent, host-capability fallback, and the boundary against adjacent research tools. Nothing material is missing for a 2-parameter, non-mutating render tool.

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 schema already documents title, results, id, url, text, and metadata – this sets the baseline at 3. The description adds ordering semantics ('Pass existing results in the desired order') and reinforces that the payload must be pre-existing rather than newly fetched, which is meaningful beyond the field-level docs.

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 and resource – present already-retrieved results as source cards with a text-list fallback – and immediately bounds the scope with negations ('Does not search, crawl, fetch URLs, verify sources, or consume search credits'). This cleanly separates it from siblings like search, crawl, and sitemap, which is exactly the confusion an agent would otherwise face.

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?

Gives an explicit trigger ('when the user wants to browse sources or a visual list helps the task'), an explicit anti-trigger ('Do not call for intermediate research results or when a text answer is sufficient'), and enumerates the excluded operations. There is also a prerequisite: results must already exist. Nothing about when to select this tool is left to inference.

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