broad_search

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

Annotations already declare readOnly/idempotent/non-destructive/open-world, and the description adds meaningful behavior beyond them: missing sources are skipped and reported, and web_index_fallback results never count as successful native platform searches. Pagination, rate limits, and return shape remain undisclosed.

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?

Purpose is front-loaded in the first sentence and each subsequent sentence adds non-redundant semantics for a specific parameter. The awkward line wrapping and absence of any framing for rounds/max_results costs it a point but nothing 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?

For an 8-parameter, no-output-schema search tool with annotation coverage on safety, the description covers source selection and fallback well but leaves multiple tuning parameters (rounds bounds, max_results, per_query_limit, notify) unexplained, leaving the agent to guess at invocation-affecting knobs.

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 0% for 8 parameters, so the description carries the full burden. It explains sources, queries, and web_index_fallback well (and implies rounds), but topic, notify, max_results, and per_query_limit are left undocumented in both schema and description.

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 sentence names a specific verb and resource ('Search all configured sources') and adds distinguishing scope ('bounded query expansion rounds with citations and coverage'), which separates it from the single-page fetch_page/fetch_pages siblings. It does not explicitly name those siblings, so it stops short of a 5.

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 gives conditional context for sources=None vs explicit sources and for enabling web_index_fallback, which is useful when-to-use signal. However, it never states when to prefer broad_search over source_status or fetch_page, nor any when-not-to-use condition, so usage is implied rather than prescribed.

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