resume_gapCompare résumé skills with Columbus, Ohio job postings, or with one pasted job description. Résumé is not stored.
| Name | Required | Description | Default |
|---|---|---|---|
| family | No | Job family for the Columbus postings check; required unless job_ad is given. | |
| job_ad | No | Plain text of one job description; lists the skills it names that the résumé shows and does not show. | |
| resume_text | Yes | Plain text of the résumé. |
Changes observed during successful MCP inspections.
Input schema / examplesAdded value: +[
+ {
+ "job_ad": "Data analyst. Required: SQL, Python and Tableau.",
+ "resume_text": "Data analyst with SQL and Excel experience building weekly reports."
+ }
+]Input schema / properties / family / descriptionAdded value: +"Job family for the Columbus postings check; required unless job_ad is given."Input schema / properties / job_adAdded value: +{
+ "description": "Plain text of one job description; lists the skills it names that the résumé shows and does not show.",
+ "maxLength": 60000,
+ "minLength": 1,
+ "type": "string"
+}Input schema / requiredPrevious value: -[
- "resume_text",
- "family"
-]New value: +[
+ "resume_text"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds a genuinely non-obvious behavioral fact — "Résumé is not stored" — which addresses a real user/agent privacy concern that structured fields do not convey.
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 lean sentences with the core action front-loaded and the privacy note trailing. Every clause carries information; there is no filler or repetition of the title.
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 read-only, non-destructive analysis tool with no output schema, the description covers the two input modes and the data-handling behavior, which is enough to invoke it correctly. It does not preview the shape of the gap result, though the job_ad parameter text hints at it.
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 every parameter (family enum, job_ad length bounds, resume_text length bounds, and the family-required-unless-job_ad rule) is already documented. The description reinforces the mode selection and privacy stance but adds no new parameter-level meaning, so the baseline 3 is appropriate.
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?
Specific verb ("Compare") plus resource ("résumé skills") and both scopes are spelled out: Columbus, Ohio job postings or a single pasted job description. No sibling tool overlaps, and an agent immediately knows this performs a résumé-vs-posting skill gap comparison.
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 clearly establishes the two usage modes (aggregate Columbus postings vs one pasted job description), so an agent knows the tool's applicable context. It stops short of stating when to prefer one mode over the other or any exclusions, which the schema's "required unless job_ad is given" note partially covers.
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.