KIRHA Search

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds genuine context beyond that: aggregated multi-provider execution, web-search fallback, raw per-provider results, and 'nothing to configure.' It stops short of latency, cost, rate limits, or failure behavior, which would be useful for a fan-out tool.

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?

Front-loaded with the core value proposition and scoping trigger before the domain examples. The example enumeration is long, but each item aids routing; the closing 'Ask in plain language' sentence is slightly redundant with the schema's plain-language framing.

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, the description at least characterizes the return shape ('each provider's raw result'). For a fan-out aggregator, it leaves result volume, provider-attribution format, and behavior when no provider matches unanswered, but the essential call contract is complete.

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% and both parameters already carry guidance in the schema, including the focus-slug caution and the 'be specific' advice for query. The description adds only 'Ask in plain language, there is nothing to configure,' which is marginal beyond the schema baseline.

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 names a specific mechanism (KIRHA plans the query, calls the right providers, returns each provider's raw result) over a concrete resource set (50+ specialized providers covering prices, filings, patents, trials, CVEs, flights, weather). An agent can tell exactly what kind of answer this tool produces, and it explicitly positions itself against a generic web search.

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?

Explicit trigger condition: 'Call this tool whenever an answer depends on facts that change over time or that you should not state from memory.' It also states the fallback boundary ('when no specialized provider fits, it falls back to web search, so it can replace a generic web search') and the focus param carries its own when-not guidance ('Leave it out unless the user asks for a specific vertical').

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