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

Annotations only cover the safety profile (readOnly, non-destructive, closed-world); the description carries the rest and does so extensively — the 30,000-character cap, null-vs-[] semantics for searchQueries with an explicit warning that null is not evidence of no search, stopReason values, exclusion of grounding-redirect and scan-echo URLs, recovered mentions lacking position/sentiment, sourcesNameSitesOnly behaviour, and data-availability cutoffs (Oct/Jul 2026). It also flags that the returned text, URLs and searches are third-party content to be quoted but never obeyed, which is a genuine safety disclosure.

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 content list is front-loaded in the first sentence, and with no output schema every caveat (null semantics, excluded link classes, per-provider quirks, date cutoffs) earns its place. The cost is structure: one dense block with long em-dash-chained sentences and no segmentation, which makes the edge cases harder to scan than they need to be.

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?

With no output schema and a genuinely complex return shape, the description documents nearly every field, including the ones that can be null for non-obvious reasons and the per-engine limitations that change how a field should be read. An agent can interpret the response correctly without guessing.

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 baseline is 3, but the description adds meaning the schema lacks about maxTextChars: that textChars still reports the true length and textTruncated signals truncation even when text is suppressed. That is output behaviour tied to the parameter, not a restatement of the schema's '0 = none'.

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 opening clause states a specific verb and resource ('One AI answer in full') and immediately enumerates the payload — full response text, brands named with positions, cited vs retrieved URLs, search queries, recommended products. This is unmistakably distinct from list_ai_answers (a list) and get_citations (an aggregate), so an agent can route without opening any schema.

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?

It routes the agent to the two places an answerId comes from ('Take answerId from list_ai_answers or get_cited_url') and gives a concrete usage variant ('To read the brands, sources and searches without the whole text, pass maxTextChars (0 = no text)'). It never states when NOT to use this tool or which sibling answers citation/brand-aggregate questions instead, so it is clear context rather than full when/when-not guidance.

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