Add a supplement, variant, correction or question to an existing experience (e.g. 'on Debian 12 you also need X'). Requires FIXLORE_KEY.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| body | Yes | ||
| kind | No | supplement | |
| environment | No | Caller environment, e.g. {os:'macOS 15', runtime:'node 24', version:'wrangler 4.141', technology:'PostgreSQL 16'} |
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| kind | No | ||
| status | Yes |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "id": {
+ "type": "integer"
+ },
+ "kind": {
+ "type": "string"
+ },
+ "status": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "id",
+ "status"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare write, non-idempotent, non-destructive, closed-world. The description adds the auth requirement (FIXLORE_KEY) and that the target must already exist, which is real context beyond the annotations. It does not say whether comments are immutable/append-only, whether edits or deletion are possible, or how failures surface.
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 short sentences, front-loaded with the core action and its variants, followed by the hard prerequisite. No filler; every clause earns its place.
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?
An output schema exists, so return values need not be described, and auth is covered. But for a non-idempotent mutation with low schema coverage and a nested environment object, the description leaves out what id identifies, how environment is used, and the lifecycle/immutability of a posted comment.
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 only 25% (essentially just environment), so the description must compensate. It enumerates four of the five kind values but omits 'note' and never explains that id refers to the target experience's identifier, nor what body/environment should contain. Partial compensation at best.
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?
States a specific verb (add) and resource (supplement/variant/correction/question to an existing experience), with an inline example that makes the intent concrete. It implicitly distinguishes itself from submit_fix ('existing'), but never names the sibling or contrasts explicitly.
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 example ('on Debian 12 you also need X') and the 'existing experience' qualifier imply when this tool applies, and the FIXLORE_KEY note signals a prerequisite. However, there is no explicit when-not guidance or routing to alternatives like submit_fix or report_fix_issue, which overlap conceptually.
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.