Return the top-N California DAs by editorial severity score (descending). Use for "worst DA" / "most-disciplined DA" / ranking questions. Optional county filter. Only manually-scored records are returned.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| county | No | Optional county filter, e.g. "San Mateo" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the burden. It discloses that only manually-scored records are returned, which is a key filter. It also specifies descending order, but does not cover edge cases like empty results or invalid county.
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?
Three succinct sentences with no filler. The main action, usage, and key filter are all included efficiently.
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?
For a simple read tool with no output schema and no annotations, the description covers purpose, usage, and a key data filter. It sufficiently informs the agent about what the tool returns and its constraints.
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?
The schema covers 50% (county only), and limit lacks a description. The description clarifies 'top-N' which maps to limit, and states the county filter is optional. It adds behavioral context for both parameters.
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 returns the top-N California DAs ranked by editorial severity score in descending order. It distinguishes from sibling tools like search_das and get_da by focusing on ranking and severity. The usage examples clarify its role.
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?
Explicitly identifies when to use: for 'worst DA' or 'most-disciplined DA' ranking questions. It doesn't mention alternatives or when not to use, but the context is clear given the sibling list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool has a clearly distinct purpose: get_* retrieves specific records, search_* queries databases, top_* provides rankings, and list_* enumerates metadata. The overlap between search_cjp and search_cjp_documents is explicitly resolved in their descriptions.
All tool names follow a consistent verb_noun pattern with underscore separators: get_, search_, list_, top_. The pluralization of search_das vs get_da matches the function, and search_capost is a clear abbreviation.
15 tools is well within the ideal range for a public-records server covering four entity types. Each tool earns its place, covering retrieval, search, ranking, and metadata listing without unnecessary bloat.
The surface covers the full read-only workflow: discover databases, search records, retrieve full details, rank by severity, and navigate site pages. No obvious gaps exist for the stated purpose of exposing California justice system records.