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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety and determinism profile is covered. The description adds one genuinely useful behavioral fact beyond annotations: only *published* changes are searched (draft/unpublished content is excluded) and results are relevance-ranked rather than chronological. It does not discuss result size, truncation, or what a returned change contains.

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?

A single front-loaded sentence with no filler; the ranking behavior is tucked into a trailing clause where it is easy to miss, which slightly undercuts the otherwise efficient structure.

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 three parameters, 33% schema coverage, and no output schema, the description should carry more load. It conveys scope and ordering but omits the shape of a returned 'change', the meaning of the limit cap (max 25), and any note on empty-result behavior, leaving meaningful gaps for an agent consuming the results.

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 coverage is only 33% (locale is the sole described parameter), so the description must compensate. It does add value for the required 'query' parameter by clarifying that it matches entity-like words (company, country, subject) rather than free-form full text, but it says nothing about 'limit' or about matching behavior for multiple terms. Partial compensation only.

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 and resource combination ('search published changes') plus the matching basis (keywords naming a company, country, or subject) and result ordering ('most relevant first'). It is clearly not a fetch-by-id or list-recent tool. However, it never names the closest siblings (latest_changes, get_change), so an agent must infer the boundary itself.

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?

There is no explicit when-to-use statement, no exclusions, and no mention of alternatives such as latest_changes for browsing or get_change for retrieving a known change. The keyword-search framing only weakly implies the use case, leaving routing between the seven sibling tools to inference.

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