gdelt_context

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

Annotations are entirely absent, so the description carries the full burden of behavioral disclosure. It reveals only that results draw from the last 72 hours of GDELT-monitored news and that matching is sentence-level. It does not describe the response shape, whether results are sentences or article references, pagination behavior, or failure modes. The truncated final sentence suggests even the intended behavioral description was never completed.

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 text is short, which is normally a virtue, but the second sentence is a clear truncation: 'Search recent (last 72 hours) GDELT-monitored news for.' with a dangling 'for.' This is a structural defect, not conciseness. Sentence 1 and sentence 2 also redundantly cover the same ground ('recent GDELT coverage' vs 'recent (last 72 hours) GDELT-monitored news'), wasting one of only two sentences on repetition.

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 9 parameters, zero annotations, no output schema, and a cluster of closely related siblings (gdelt_search, gdelt_timeline, gdelt_tonechart), this description is inadequate. An agent cannot learn what the results look like, how sentence-level results are presented, or how this differs from gdelt_search. The truncated text confirms the description was left unfinished rather than deliberately minimalist.

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%, and the schema descriptions are unusually rich: query explains co-occurrence, quoted phrases, OR syntax, and domain: filters; from/timespan document the 72-hour cap and mutual exclusivity; maxrecords discloses the hard 200-row cap and absence of pagination. Per the rubric, high schema coverage sets a baseline of 3. The description adds essentially nothing about parameters beyond restating the 72-hour window already implied by the schema, so it stays at 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 first sentence states a specific verb and resource: 'Sentence-level co-occurrence search across recent GDELT coverage.' This identifies the query mode (sentence-level co-occurrence) and the data scope (recent GDELT news), which helps distinguish it from sibling tools like gdelt_search or gdelt_timeline. However, the description is truncated — 'Search recent (last 72 hours) GDELT-monitored news for.' ends mid-thought — and it never explicitly names sibling tools, so a perfect score is not warranted.

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 no guidance on when to use this tool versus alternatives. It does not name gdelt_search, gdelt_timeline, or gdelt_tonechart as alternatives, nor does it state conditions that would route an agent away from this tool (e.g., need for document-level search, aggregations, or tone analysis). The 72-hour window is a constraint rather than a usage-selection guideline. With a large family of GDELT siblings present, this lack of routing guidance is a clear gap.

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