gdelt_search

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

No annotations are provided, so the description carries the full burden. It partially compensates by disclosing behavioral constraints in parameter descriptions: GDELT only indexes roughly the last 3 months, maxrecords has a hard cap of 250, and there is no pagination cursor beyond it. However, the main description does not disclose the response format, error behavior, or what happens when no results are found.

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 concise and front-loaded with the core purpose. Parameter descriptions are detailed but not bloated, with constraints like 'Cannot be combined with timespan' and 'no pagination cursor beyond it' clearly embedded. The only minor issue is that the query parameter description is cut off mid-sentence with 'near20:\' which appears incomplete.

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 search tool with no output schema, the description covers the key operational constraints: time window limits, convenience filters, result cap, and query syntax support. The missing return-format description is a notable gap since an agent cannot predict the shape of the result. Otherwise, the tool is well-specified for invocation.

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 100%, so the schema already documents all parameters. The description adds value beyond the schema by explaining that domain, country, and language are 'convenience filters' appended to the query, and by stating mutual exclusivity between from/to and timespan. These enrich the schema but do not fully compensate for the absent output schema.

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 states a specific verb ('search') and resource ('global news coverage indexed by GDELT'). It clearly identifies the tool as the main GDELT news search entry point, and the parameter descriptions reinforce that scope. However, it does not explicitly differentiate itself from sibling tools like gdelt_context or gdelt_timeline, which is a minor gap.

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 makes clear this is the general search tool for GDELT news while siblings like gdelt_timeline, gdelt_tonechart, and gdelt_context exist for specialized views. It also documents key constraints like the inability to combine from/to with timespan and the 3-month indexing window. It could be improved by explicitly naming which sibling to use for timeline or tone analysis.

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