List discussion notes of a candidate.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| size | No | ||
| view | No | summary replaces the body with a 200-char body_preview | summary |
| include | No | Embed: user (author), candidate | |
| candidate_id | Yes | Candidate id or alias |
Changes observed during successful MCP inspections.
Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / candidate_id / descriptionPrevious value: -"Candidate ID (numeric) or alias"New value: +"Candidate id or alias"Input schema / properties / include / descriptionPrevious value: -"Include related resources: 'user' for author details, 'candidate' for full candidate payload with url_backoffice."New value: +"Embed: user (author), candidate"Input schema / properties / page / descriptionRemoved value: -"Page number"Input schema / properties / size / descriptionRemoved value: -"Page size"Input schema / properties / view / descriptionPrevious value: -"Response shape. Default `summary` replaces the full note body with a 200-char `body_preview`. Use `full` only when the full note text is genuinely needed; call hires_get_note for a single record."New value: +"summary replaces the body with a 200-char body_preview"Input schema / properties / include / descriptionPrevious value: -"Include related resources: 'user' for author details, 'candidate' for full candidate payload with profile_url."New value: +"Include related resources: 'user' for author details, 'candidate' for full candidate payload with url_backoffice."Input schema / properties / include / descriptionPrevious value: -"Include related resources, e.g. 'user' for author details"New value: +"Include related resources: 'user' for author details, 'candidate' for full candidate payload with profile_url."Input schema / properties / viewAdded value: +{
+ "default": "summary",
+ "description": "Response shape. Default `summary` replaces the full note body with a 200-char `body_preview`. Use `full` only when the full note text is genuinely needed; call hires_get_note for a single record.",
+ "enum": [
+ "summary",
+ "full"
+ ],
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true and destructiveHint=false, so the description does not need to reiterate safety. However, it adds no additional behavioral context such as pagination, default view behavior, or response format. Since there is no output schema, the description could disclose expected behavior, but it remains silent.
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 with no filler or redundancy. It is immediately readable and front-loads the core operation. This is appropriately sized for a simple read operation.
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?
With 5 parameters (including enums and embedding options) and no output schema, the description is insufficient. It does not mention pagination, the 'view' parameter's effect on response body preview, or the 'include' parameter for embedding related objects. An agent would not know how to tailor the call for desired granularity or embedded data, making the tool incomplete for practical use.
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 60%, meaning parameters like page and size lack descriptions. The tool description does not compensate for these gaps—it doesn't explain pagination or the meaning of 'view' or 'include'. An agent relying on the description alone would have no insight into these parameters, and the description adds no value beyond what the schema already provides.
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 verb and resource: 'List discussion notes of a candidate.' It distinguishes this tool from siblings like hires_get_note (singular) and hires_list_candidate_messages (different content type). However, it does not elaborate on the scope or any filtering specifics, so it's clear but not as detailed as the calibration high example.
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?
There is no guidance on when to use this tool versus alternatives. It does not mention exclusions, prerequisites, or conditions that would lead an agent to choose this over other list operations. The single sentence provides no context for decision-making beyond the basic action.
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.