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

Annotations already carry the safety profile, lowering the bar, and the description adds useful output context by promising verifiable internal source links. However, it does not reconcile the surprising readOnlyHint=false / openWorldHint=false annotations with what reads like a read-only search, nor mention pagination, result caps, or rate limiting.

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 compact, front-loaded sentences with no filler; the bilingual duplication adds bulk for a single-language agent but is purposeful localization rather than padding.

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 shape need not be explained, and the description correctly signals the source-link nature of results. But for a six-parameter tool with 33% schema coverage it leaves the filter semantics and usage context unaddressed, which is a real gap an agent will hit when constructing a call.

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 only 33%: the schema documents query and form_type, but limit, market, date_from, and date_to have titles only. The description compensates for none of this — it never mentions market switching, date ranges, or the result limit, so four filters remain ambiguous.

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 with explicit scope: searching US SEC filings and China listed-company announcements, and it names the return artifact (verifiable internal source links). The domain is narrow enough to distinguish it from search_research, search_meetings, and search_visuals, though it never explicitly contrasts itself with those siblings.

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?

The description says what the tool does but never when to choose it over get_evidence or search_research, nor when not to use it (e.g., for non-US/China markets). No prerequisites, no guidance on which filters to combine.

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