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

With no annotations provided, the description carries the full burden and does add real behavioral context: results include highlighted snippets, responses are paged with page_size items at a time, and the response exposes a total that determines whether another page=N call is needed. It does not cover matching semantics (exact vs fuzzy), rate limits, or cost of broad queries, but the pagination/large-result warnings are the operationally important disclosures.

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 core purpose is front-loaded and the pagination warning is well placed, but the description is repetitive ('Returns page_size results at a time' partly restates the page_size caution) and it drags in HTTP response boilerplate ('**200**: Successful Response... Content-Type: application/json') that is noise for tool selection.

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?

No output schema exists, so the description must describe returns, and it does: highlighted snippets plus a total count plus paged results. Combined with full schema coverage on all five parameters, an agent has enough to invoke and page correctly; only matching semantics and the relative merit versus the entity-specific search tools are missing.

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 100%, so the baseline is 3, but the description adds genuine operational meaning on top of the schema by telling the agent to keep page_size at 5-10 rather than the schema's stated max of 100, and by explaining the page parameter in terms of the returned total. Date-range parameters (gte/lte) are not discussed in the description, but their schema docs are adequate.

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 concrete verb and resource ('Search Vysion's leaked data database') and enumerates the searchable entity types (keyword, domain, email, username, IP, credential), which makes the broad-scope nature of this tool clear next to the narrower by_* siblings. It does not explicitly name those siblings or state that it is the general-purpose counterpart to search_leaks_by_email/search_leaks_by_ip, so a small amount of differentiation is left implicit.

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?

'Primary tool for leak investigation' gives a high-level usage signal, and the pagination instructions tell the agent how to continue a result set. However, there is no explicit when-not guidance and no mention of when the entity-specific siblings (search_leaks_by_email, search_leaks_by_hash, etc.) would be the better choice.

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