litigation_history

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

Annotations already carry the safety and exhaustiveness profile (readOnlyHint=true, openWorldHint=true), so the bar is lower. The description adds real provenance context: the specific legal databases screened and the categories of enforcement records covered, which helps an agent calibrate coverage expectations. It does not address result format, data freshness, or source-coverage limitations, but these are secondary given the annotations.

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?

Exactly two sentences with no filler: the first packs sources, record types, and subject scope; the second delivers the sibling distinction. The most decision-relevant information is front-loaded before the alternative routing.

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 a read-only research tool with one required nested parameter and no output schema, the description covers the subject, sources, record categories, and the key alternative thoroughly. Two gaps remain: it never hints at the return shape (list of case citations vs. narrative findings), and the `sector`-as-subject option is not reconciled with the 'company or promoter name' subject phrasing. These are minor for invoking the tool correctly, hence a 4 rather than a 5.

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 0% at the top level, and the only required field (`company`) is undescribed in the schema, so the description must compensate. It partially does by stating the subject can be a company or promoter name, giving the `company` parameter meaning the schema lacks. However, it adds nothing about `date`, `listed`, `country`, or `companyDomain`, and the India-specific source list sits awkwardly with the `country: global` option — compensation is only partial.

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 description uses a specific verb ('screens'), names precise sources (SEBI, NCLT, IndianKanoon, LiveLaw, Bar & Bench), and enumerates concrete record types (litigation, regulatory penalties, insolvency proceedings, director disqualification). It also explicitly distinguishes itself from the closest sibling, negative_news, so an agent can differentiate the tools without opening schemas.

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 second sentence gives an explicit routing rule: this tool is for hard legal/regulatory records, while negative_news covers general press/employee sentiment. That is a clear when/when-not with a named alternative, matching the structure of the strongest calibration examples. It only covers one sibling, but negative_news is the genuinely confusable one; other siblings are distinguished by name alone.

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