How cases with a candor allegation (falsification, omission, or lack of candor) were resolved in the decided record: the favorable rate with vs without such an allegation, when the judge found a deliberate falsification vs when the applicant rebutted it, and when the applicant corrected the record before being confronted. Counts and denominators throughout. Descriptive, never a prediction.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral details: it is descriptive (not predictive), provides counts and denominators, and explains the scope (allegations of falsification, omission, lack of candor). No contradictions with annotations.
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 a single paragraph that front-loads the main purpose but includes some redundancy (e.g., 'Counts and denominators throughout' reemphasizes prior information). It could be slightly more concise by omitting repetitive phrases.
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 no parameters and no output schema, the description fully explains what the tool returns. It covers the key analytical breakdowns and sets expectations (descriptive, not predictive). Minor lack of explicit usage guidelines prevents a 5.
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 tool has no parameters, so schema coverage is trivially 100%. The description compensates by explaining the nature of the output (favorable rates, counts, denominators), adding meaning beyond the empty input schema.
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 provides outcome breakdowns for candor allegation cases, including specific sub-analyses (favorable rates, deliberate falsification, rebuttals, corrections). It distinguishes itself from siblings like get_case and get_statistics by focusing on a specific aggregated analysis.
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 use for descriptive analysis of candor outcomes, noting 'Descriptive, never a prediction.' However, it does not explicitly state when to use this tool versus siblings like get_statistics or search_cases, leaving usage context partially implicit.
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.