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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds genuinely useful behavior: separate sponsored and organic arrays, organic-only pagination, pinned and flagged sponsored placements, and possible coming-soon placeholders. That sponsored-vs-organic split and the placeholder caveat are real disclosure beyond structured fields, though scoring/filtering behavior (min_score) is left unexplained.

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?

Dense and front-loaded: purpose first, then pagination defaults, then the alternative tool, then result-structure caveats. Every sentence carries information, though the run of clauses about sponsored/organic arrays makes the tail slightly hard to parse in one pass.

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 accepts the burden of describing the return shape and does so (paginated summaries, sponsored/organic arrays, separate pagination, placeholder flags), which is strong for a 9-parameter search tool. Gaps remain around the enum kind values and min_score, so it is not fully self-sufficient.

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 carry parameter meaning. It usefully explains that query also matches use cases and audience, that use_case/audience filters do case-insensitive substring matching, and that region includes global sources, but it is silent on kind, category, min_score, and offset semantics.

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?

States a specific verb (Search) plus the resource and domain scope (curated water, environment, terrain and civil engineering sources), and explicitly distinguishes itself from get_source, which serves the full-record need. An agent can route between search_sources and get_source without opening either schema.

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?

Names the alternative (get_source for full evidence and enrichment) and states the default/maximum page size, giving clear context for when to search summaries versus fetch detail. It does not state explicit when-not-to-use conditions or how it relates to sibling listing tools like top_sources or list_categories.

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