Submit a career site application: creates the candidate and runs the pipeline automation.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | |||
| phone | No | ||
| job_id | Yes | ||
| resume | No | ||
| source | No | Source identifier | |
| answers | No | Form answer objects | |
| last_name | Yes | ||
| first_name | Yes | ||
| company_slug | Yes | ||
| linkedin_url | No |
Changes observed during successful MCP inspections.
Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / answers / anyOfPrevious value: -[
- {
- "items": {
- "additionalProperties": {},
- "type": "object"
- },
- "type": "array"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "items": {
+ "type": "object"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / answers / descriptionPrevious value: -"Array of form answer objects"New value: +"Form answer objects"Input schema / properties / company_slug / descriptionRemoved value: -"Company slug identifying the career site"Input schema / properties / email / descriptionRemoved value: -"Applicant email address"Input schema / properties / first_name / descriptionRemoved value: -"Applicant first name"Input schema / properties / job_id / descriptionRemoved value: -"Job ID to apply to"Input schema / properties / last_name / descriptionRemoved value: -"Applicant last name"Input schema / properties / linkedin_url / descriptionRemoved value: -"Applicant LinkedIn profile URL"Input schema / properties / phone / descriptionRemoved value: -"Applicant phone number"Input schema / properties / resume / anyOfPrevious value: -[
- {
- "additionalProperties": false,
- "properties": {
- "data": {
- "description": "Base64-encoded file content",
- "type": "string"
- },
- "file_name": {
- "description": "Resume file name (e.g. resume.pdf)",
- "type": "string"
- },
- "mime_type": {
- "description": "Resume MIME type (e.g. application/pdf)",
- "type": "string"
- }
- },
- "required": [
- "data",
- "file_name",
- "mime_type"
- ],
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "properties": {
+ "data": {
+ "description": "Base64 file content",
+ "type": "string"
+ },
+ "file_name": {
+ "type": "string"
+ },
+ "mime_type": {
+ "description": "e.g. application/pdf",
+ "type": "string"
+ }
+ },
+ "required": [
+ "data",
+ "file_name",
+ "mime_type"
+ ],
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / resume / descriptionRemoved value: -"Resume file upload (base64 encoded)"Input schema / properties / source / descriptionPrevious value: -"Application source identifier"New value: +"Source identifier"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool creates a candidate and runs pipeline automation, which adds behavioral context beyond the annotations (readOnlyHint=false, destructiveHint=false). It clearly indicates side effects without contradicting annotations. However, it does not elaborate on the details of the pipeline automation or potential irreversible consequences, so it is not exhaustive.
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, concise sentence that front-loads the primary action. It is free of redundancy and easy to parse. However, given the tool's complexity (10 parameters, multiple roles), a bit more detail might be warranted, but as a short description it is appropriately structured.
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?
The description is incomplete for an agent to use the tool correctly. It does not explain the purpose of parameters like resume, answers, source, or linkedin_url, nor does it describe what 'pipeline automation' entails. With no output schema and low schema coverage, the description should provide more context to ensure correct invocation.
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 description offers no explanation of the parameters. With schema description coverage at only 20%, the agent is left to infer the meaning of key required fields like company_slug, job_id, first_name, last_name, and email from the schema, which itself lacks descriptions for most. The description does not compensate for this low coverage.
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 states a clear action ('Submit a career site application') and specifies the outcome ('creates the candidate and runs the pipeline automation'). It is specific enough to indicate the tool's scope, but it does not explicitly contrast with similar sibling tools like hires_create_application or hires_create_candidate, leaving some ambiguity about exact boundaries.
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 provides no explicit guidance on when to use this tool versus alternatives. It only implies that it is for career site submissions, but there is no mention of scenarios to avoid or when to prefer a different tool. This is a significant gap given the large number of sibling tools.
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.