find_discrepancies

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

With no annotations, the description carries the behavioral burden. It explains a non-obvious default—'keeps only events reported by 2+ agencies, since a lone report cannot disagree with itself'—which is genuinely useful. The read-only nature is implied by 'Return events,' and the output schema covers return details, so the description does not need to repeat them.

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 description is three sentences with no filler: purpose, parameter relationship to find_events, then default behavior and use cases. The most identifying information is front-loaded, and every sentence adds value.

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 tool with 16 parameters, no annotations, and an output schema, the description is largely complete: it explains what the tool returns, how it relates to find_events, its default filtering behavior, and when it is useful. The main minor gap is the lack of explicit contrast with sibling tools such as compare_sources.

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%, and the description compensates only partially by saying 'Same query params as find_events, plus tunable spread thresholds.' This tells the agent which parameters are inherited and which category the extra ones fall into, but it does not enumerate or define the threshold parameters; the property names like min_magnitude_spread and min_location_spread_km carry much of the semantic load.

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, 'Return events where agency reports disagree past the given thresholds,' is a specific verb+object statement that makes the tool's core function unmistakable. It also distinguishes itself from find_events by noting it adds 'tunable spread thresholds,' so an agent can tell this is the discordance-focused variant of the event 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?

The description provides clear context: 'Useful for journalism, QA of preliminary feeds, or surfacing where the global picture is genuinely uncertain.' It also references find_events for shared query parameters, which orients the agent. However, it does not explicitly state when not to use it or compare it with alternatives like compare_sources.

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