add_noteAppend a free-text note to an application timeline — recruiter call summaries, interview instructions, pasted messages. Multiline markdown is fine. Example: add_note({application_id: "…", text: "Recruiter: team of 5, on-call rotation, offer range 85-95k"}).
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| application_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=false and destructiveHint=false. Description adds that input is 'free-text' and 'multiline markdown', but no additional behavioral traits beyond that.
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?
Three concise sentences plus an example. Front-loaded with purpose, no wasted words.
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 two-parameter tool with no output schema, the description fully covers what the agent needs: action, resource, input format, and example. No missing context.
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 has 0% description coverage, so description compensates by explaining 'free-text note' and giving an example with both parameters, clarifying that application_id is a UUID and text accepts multiline markdown.
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?
Clearly states action (append note) and resource (application timeline). Examples like 'recruiter call summaries' distinguish from sibling tools like add_application and log_interview.
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?
Provides specific use cases (call summaries, instructions, messages). Implicitly suggests when not to use (structured data should go to log_interview), but lacks explicit alternatives.
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.
Every tool targets a distinct resource and action: application, note, analysis attachment, file attachment, interview file, application detail, due actions, planned schedule, application listing, interview logging, and application updates. Even the three 'attach' tools are clearly differentiated by purpose (analysis vs CV/cover letter vs interview prep). The only potential overlap between get_due and get_planned is explicitly resolved in the descriptions.
All tools follow a consistent verb_noun pattern in snake_case (add_application, get_application, list_applications, update_application, attach_analysis, log_interview, etc.). The verb prefix accurately reflects the action, and nouns are singular for single-item operations and plural for list operations, maintaining a predictable convention.
With 11 tools, the server is well-scoped for a job application tracking domain. Each tool covers a necessary function without redundancy, and the count is neither sparse nor overwhelming.
The tool set covers the full lifecycle of an application: create, read, list, update, plus notes, attachments, analysis, and interview logging. Minor gaps exist—there is no explicit delete or archive tool (though status updates can archive), and interviews cannot be directly updated or removed after logging—but these are workable within the existing surface.