Get the structured AI score for an application, including per-criterion scores, justifications, and follow-up questions. Returns null score if the application has not been AI-scored.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Application ID. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and destructiveHint. The description adds the behavioral detail that null is returned if the application has not been AI-scored, which is not in annotations. No contradictions.
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 two sentences, front-loading the key purpose and return behavior. Every sentence is necessary and succinct.
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 get tool with one parameter and no output schema, the description adequately explains what to expect (structured score, null if unscored). It is complete enough for the tool's complexity.
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 parameter 'id' is already documented. The description does not add further meaning beyond what the schema provides, warranting a baseline score of 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 retrieves the structured AI score for an application, specifying contents (per-criterion scores, justifications, follow-up questions) and the null case. This distinguishes it from sibling tools like hires_get_application or hires_get_evaluation.
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 for retrieving AI scores but does not explicitly state when to use this over alternatives like hires_get_evaluation or hires_list_application_evaluations. No exclusions or when-not-to-use are provided.
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.
Most tools have clearly distinct purposes due to specific entity and action combinations. However, with 133 tools, there is some overlap (e.g., multiple ways to move applications) and similar-sounding operations (e.g., batch_remove_tags vs remove_candidate_tag) that could cause confusion. The detailed descriptions help but the sheer number increases ambiguity.
All tools follow a consistent 'hires_verb_noun' pattern with snake_case. Verbs are descriptive (create, list, get, delete, update, batch) and nouns match the domain entities (candidate, application, job, etc.). No mixing of conventions like camelCase or inconsistent verb styles.
133 tools is excessive for a typical server scope. While a full-featured ATS requires many operations, this count suggests insufficient aggregation. Tools for similar entities (e.g., multiple update/delete variants) could be consolidated. The high number overwhelms the tool surface and increases complexity.
The tool set covers core CRUD operations for major entities (candidates, applications, jobs, companies, users, messages, forms, etc.) plus batch operations, webhooks, and advanced features like AI scoring and nurture campaigns. Minor gaps exist (e.g., no direct reporting/analytics tools), but most workflows can be executed.
