Grant/denial statistics over decided hearing-level DOHA cases, grouped by year or by guideline, always with sample sizes. Same population rules as the site's Insights page.
| Name | Required | Description | Default |
|---|---|---|---|
| by | No | Grouping (default year) | |
| year_to | No | ||
| guideline | No | Optional single guideline letter A-M to scope to | |
| year_from | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and destructiveHint=false, so the description adds value by stating 'always with sample sizes' and specifying grouping options. This provides behavioral context beyond the annotations without contradiction.
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?
Two sentences with no fluff. The main action and key details (grouping, sample sizes, population rules) are front-loaded, earning their place.
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 tool with 4 parameters and no output schema, the description could be more complete. It lacks details on the output structure (beyond sample sizes) and does not explain the 'same population rules' reference. With good annotations, the bar is lower, but the description still feels somewhat incomplete.
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 50%, with 'by' and 'guideline' documented. The description mentions grouping by year or guideline, partially covering the parameters. However, year_from and year_to lack schema descriptions and the description does not explain their format or range, leaving a gap for undocumented 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 retrieves grant/denial statistics over decided hearing-level DOHA cases, with grouping by year or guideline. The verb 'get' and resource 'statistics' are specific. It distinguishes from sibling tools like get_case or search_cases by focusing on aggregate data.
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 mentions 'Same population rules as the site's Insights page,' which provides some context about the data source, but it does not explicitly state when to use this tool vs alternatives or provide guidance on prerequisites or filtering.
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.
Each tool targets a distinct aspect of the DOHA case record: searching, fetching full case, finding similar cases, and four different statistical analyses (candor, conduct recency, timelines, overall statistics). There is no ambiguity between tool purposes.
Most tools use a 'get_' prefix, but 'search_cases' uses 'search_' and 'similar_cases' uses an adjective instead of a verb. This mix of conventions, while readable, lacks a consistent pattern.
Seven tools is well-scoped for the domain of exploring DOHA security clearance decisions. It covers both data retrieval (search, case fetch, similarity) and various descriptive statistics without being overwhelming.
The tool surface covers core operations: search, case detail, similarity, and key statistics. Minor gaps exist, such as no tool for listing all guidelines or judges, but these are not essential for the primary analysis purpose.