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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description goes beyond by disclosing deduplicated story clusters, explicit zero rows, named empty_aspects, and the cold-start behavior of the embedding model. These are valuable behavioral traits not conveyed by 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?

Although the description is substantial, every sentence carries unique operational information: purpose, exclusions, output grid, data semantics, parameter formats, prerequisite, and performance note. It is densely packed with no filler and is logically ordered, making it easy to parse.

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 fully specifies the return structure: aspect × time-bucket grid, cluster_count, weighted mean/variance, polarity histogram, breakdowns, and top-k URLs. It also covers edge cases (zero rows, empty_aspects) and performance characteristics. For a complex 7-parameter tool, this is highly 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 description coverage is 0%, so the description must compensate. It explains geo_id, aspects with an enumerated subset, window_start/end as ISO-8601 with defaults, and bucket values. top_k is implied via 'top-k canonical source URLs', but langs is not explicitly described, leaving a small gap in full parameter coverage.

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 clearly identifies the tool as destination sentiment/trend aggregates, with a specific verb ('search') implied and a resource (destination sentiment). It distinguishes itself from siblings by explicitly contrasting with real-time alerts on the standing-query/event side. The purpose is specific and actionable.

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?

It states exactly when to use it ('how do travelers feel about X over time') and when not to ('never for real-time alerts'), pointing to the alternative side. It also instructs to find geo_ids with resolve_geo, providing a concrete cross-tool dependency. This is explicit guidance with alternatives.

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