track_legal_changes

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

Annotations are not provided, so the description carries the burden of behavioral disclosure. It discloses that results are saved to a result_set_id (a side effect), which is important behavioral context. However, it does not mention pagination behavior (though limit/offset parameters are in the schema), rate limits, or whether the operation is read-only or mutates state. The side effect of creating a result set is disclosed, which is helpful, but other behavioral traits like the default publisher 'DU' are not highlighted. Overall, it adds some value beyond the schema but misses a full disclosure of side effects beyond the result_set_id.

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 well-structured, front-loading the core purpose in the first line. The examples are compact and clearly illustrate usage without excessive verbosity. It earns extra for the examples, which are useful and not redundant. Slightly longer than necessary but justified by the multiple usage patterns.

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?

The tool is moderately complex, has an output schema, and all parameters are documented. The description adds key context: the result_set_id side effect and the filter_results workflow, which is essential for an agent to correctly use the tool in a multi-step process. The examples cover common parameter combinations. However, it doesn't mention return format details beyond the output schema, but that's acceptable given the output schema exists. Overall, it's complete for an agent to call it correctly.

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 semantic context by explaining the meaning of the result_set_id and how keywords work (AND logic) along with examples. It also clarifies the date_from is required and shows typical usage patterns. Since the schema already does heavy lifting, the description complements it well with practical examples and the filter_results integration, which is more than baseline 3.

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 states the tool tracks legal changes and new publications within a date range, returning acts published or modified in that range. It explicitly distinguishes itself from sibling tools like search_legal_acts and browse_acts by focusing on changes over time. 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?

The description provides explicit usage guidance: it explains that results are saved to a result_set_id and can be narrowed using filter_results, giving concrete examples of when to use this tool versus filtering. It also provides multiple usage examples covering different parameter combinations (date, keywords, publisher). This clearly tells an agent when and how to use it, and implicitly when not to (when no date range is needed, other tools may be more appropriate).

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