message_applicantMessage an applicant. Held with a summary first; the candidate gets it in Job Spotter and by email. A ready-to-read summary is in say.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| thread_id | No | ||
| application_id | No | Application id, from prepare_application or list_applications. | |
| confirmation_token | No | The token from a held answer, sent with exactly the same other inputs once the person has agreed to its summary. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (destructiveHint=true, openWorldHint=true, idempotentHint=false). The description adds real behavioral context beyond them: the message is held behind a summary before sending, and it reaches the candidate both in-app and by email. The reference to a `say` summary field adds further behavioral detail.
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 short sentences with the core action front-loaded. The opening sentence merely restates the title, but the remaining lines are economical and carry new 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?
For a non-idempotent, destructive mutation with no output schema, the description sketches the hold-and-confirm flow and delivery channels, which is useful. However it leaves `text`/`thread_id` undefined and mentions `say` without explaining how to read or use 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?
Two of four parameters (text, thread_id) are undocumented in the schema and untouched in the description, and the description instead references `say`, which is not a parameter at all. With only 50% schema coverage, the description fails to compensate for the gaps.
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 gives a clear verb+resource ("Message an applicant") and clarifies the delivery target. It does not distinguish this tool from siblings like reply_to_employer or reject_applicant, so it is clear but not differentiated.
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?
Usage is only implied via "Held with a summary first," which hints at a two-step draft/confirm flow but never says when to prefer this over sibling outreach tools or what prerequisites apply. No explicit when/when-not guidance is 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.