US Government Open Data MCP

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the dataset size ('262K+ records') and types of content ('enforcement actions, indictments, settlements, and policy announcements'), which adds some context. However, it does not disclose critical behavioral traits such as whether this is a read-only operation, potential rate limits, authentication needs, or pagination behavior (beyond what the schema implies). For a search tool with zero annotation coverage, this is a significant gap.

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 appropriately sized and front-loaded, with the core purpose stated first. Each sentence adds value: the first defines the tool, the second lists content types, the third specifies filtering and sorting, and the last two enumerate components and topics. There is zero waste, and the structure efficiently conveys essential information without redundancy.

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?

Given the tool's complexity (search with 5 parameters), no annotations, and no output schema, the description provides a good overview but has gaps. It covers the dataset scope, content types, and high-level filtering, but lacks details on behavioral traits (e.g., safety, limits) and output format. Without annotations or output schema, the description should do more to compensate, but it is adequate for a basic search tool.

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 five parameters with descriptions and enums. The description adds minimal value beyond the schema by mentioning 'Filter by title keyword' and 'sort by date', which are already covered in the schema. It does not provide additional syntax, format details, or examples beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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's purpose: 'Search DOJ press releases (262K+ records covering all DOJ divisions).' It specifies the verb ('Search'), resource ('DOJ press releases'), and scope ('262K+ records covering all DOJ divisions'). It distinguishes from sibling tools (e.g., 'doj_blog_entries', 'doj_press_release_detail') by focusing on search functionality across a large dataset rather than blog content or individual release details.

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 implies usage by listing filterable components (e.g., 'FBI, DEA, ATF') and topics (e.g., 'Drug Trafficking, Cybercrime'), suggesting when to use it for broad searches across DOJ divisions. However, it does not explicitly state when to use this tool versus alternatives (e.g., 'doj_press_release_detail' for individual releases) or provide exclusions. The guidance is contextual but lacks explicit comparisons or prerequisites.

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