Send a message in an existing conversation. Accepts room_name (from list_conversations) or talent_slug (from search_talent). Use start_conversation first if no conversation exists yet. Requires employer authentication.
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes | Message text to send | |
| room_name | No | Room name from list_conversations | |
| talent_slug | No | Talent slug (from search_talent results) — resolves to room name automatically |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description is the primary source of behavioral disclosure. It states that authentication is required, which is useful context for a mutation tool. However, it does not mention side effects beyond 'send', potential errors (e.g., invalid room_name), or whether the operation is reversible. For a mutation, this partially covers the burden but lacks depth.
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 with no fluff. The first sentence states the core purpose clearly, and the second provides usage guidance and authentication. It is front-loaded with the primary action and efficient in conveying all necessary information.
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 covers the main usage and prerequisites, but leaves ambiguity about whether at least one of room_name or talent_slug is required (the schema marks both optional, yet sending a message without a conversation seems impossible). It does not address what happens if both are provided or if neither is provided, nor does it describe error handling or return value. Given the schema has no output schema and the tool is relatively simple, this is a moderate gap.
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 schema already describes all parameters (100% coverage), but the description adds meaning by explaining the provenance: room_name comes from list_conversations and talent_slug from search_talent, and that talent_slug 'resolves to room name automatically'. This clarifies the functional relationship between parameters and provides context the schema does not.
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 verb 'send' and the resource 'a message in an existing conversation', which is precise and distinct from starting a conversation. It also distinguishes itself from start_conversation by explicitly stating it targets an existing conversation.
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 explicit guidance on when to use this tool: it requires an existing conversation, and directs to start_conversation if none exists. It also tells where to obtain room_name (from list_conversations) and talent_slug (from search_talent), which are clear prerequisites. The authentication requirement is also stated.
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 resource and action: job posting vs job browsing vs job management vs company management vs talent search vs profile editing vs messaging vs application tracking. Even similar tools like get_companies and search_companies are clearly differentiated by purpose and parameters. Overlapping concepts (e.g., post_job_public vs create_company_job) have explicit differences in authentication and cost.
All tools use snake_case and follow a verb-first pattern (add_, get_, create_, update_, delete_, search_, list_, send_, etc.). There are minor deviations like 'show_company_job' instead of 'get_company_job' and 'mark_message_read' which is a verb+noun+adjective, but the overall style is consistent and predictable across the 41 tools.
With 41 tools, this is well into the 'too many' range (25+). While the breadth reflects a comprehensive jobs platform, the number is excessive for an agent to efficiently navigate. Many tools could be consolidated (e.g., profile management could merge add_education/add_experience/update_profile, or company perks could be combined with profile updates). The tool count detracts from usability.
The tool set covers the full lifecycle: job posting (create, update, delete, list), job discovery (browse, search, related), company management (profile, perks, tech stack), talent search and messaging, application tracking (save, get, remove, update status), and data analytics (salary, statistics). Minor gaps exist—no delete/update for education or experience, no explicit 'close job' action—but these are edge cases and agents can work around them.