Posts a message on one of YOUR cases that is still open (on a dispute, only whoever opened it). Text only: files are attached from the browser.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Your message (1 to 10000 characters). | |
| caseId | Yes | Id of the case (my_cases gives it). |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | Always true: the message has been added to the case. | |
| case | Yes | Id of the case that was replied to. |
Changes observed during successful MCP inspections.
Input schema / allOfRemoved value: -[
- {
- "anyOf": [
- {
- "required": [
- "caseId"
- ]
- },
- {
- "required": [
- "casoId"
- ]
- }
- ]
- },
- {
- "anyOf": [
- {
- "required": [
- "text"
- ]
- },
- {
- "required": [
- "texto"
- ]
- }
- ]
- }
-]Input schema / properties / casoIdRemoved value: -{
- "deprecated": true,
- "description": "DEPRECATED alias of `caseId`: it still works, but use `caseId` (it will be removed in a future round, no date yet). Id of the case (my_cases gives it).",
- "type": "string"
-}Input schema / properties / textoRemoved value: -{
- "deprecated": true,
- "description": "DEPRECATED alias of `text`: it still works, but use `text` (it will be removed in a future round, no date yet). Your message (1 to 10000 characters).",
- "type": "string"
-}Input schema / requiredAdded value: +[
+ "caseId",
+ "text"
+]Input schema / x-bernuvia-aliasesRemoved value: -{
- "caseId": "casoId",
- "text": "texto"
-}Input schema / properties / caseId / descriptionPrevious value: -"Id del caso (lo da my_cases)."New value: +"Id of the case (my_cases gives it)."Input schema / properties / casoId / descriptionPrevious value: -"ALIAS RETIRADO de `caseId`: sigue funcionando, pero usa `caseId` (se quitará en una tanda futura, aún sin fecha). / DEPRECATED alias of `caseId`. Id del caso (lo da my_cases)."New value: +"DEPRECATED alias of `caseId`: it still works, but use `caseId` (it will be removed in a future round, no date yet). Id of the case (my_cases gives it)."Input schema / properties / text / descriptionPrevious value: -"Tu mensaje (1 a 10000 caracteres)."New value: +"Your message (1 to 10000 characters)."Input schema / properties / texto / descriptionPrevious value: -"ALIAS RETIRADO de `text`: sigue funcionando, pero usa `text` (se quitará en una tanda futura, aún sin fecha). / DEPRECATED alias of `text`. Tu mensaje (1 a 10000 caracteres)."New value: +"DEPRECATED alias of `text`: it still works, but use `text` (it will be removed in a future round, no date yet). Your message (1 to 10000 characters)."Output schema / properties / case / descriptionPrevious value: -"Id del caso al que se ha respondido."New value: +"Id of the case that was replied to."Output schema / properties / ok / descriptionPrevious value: -"Siempre true: el mensaje se ha añadido al caso."New value: +"Always true: the message has been added to the case."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and discloses real behavioral traits: text-only (no file uploads through this tool; files come from the browser), the case must be open, and on a dispute only the opener may post. It does not cover auth requirements, error behavior on a closed case, or rate limits, so it is strong but not exhaustive.
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 tight sentences with the core action front-loaded and the constraints appended; every clause carries meaning and nothing is padded.
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 post action the description covers ownership, case state, and the text-only limitation, and an output schema exists to explain the return. Only minor gaps (failure behavior on closed cases, no alternative routing) remain.
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 coverage is 100%: text (1-10000 chars) and caseId (sourced from my_cases) are already documented. The description only reinforces the text-only constraint and does not add format or syntax detail beyond the schema, so the baseline of 3 applies.
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 (posts a message) and resource (one of YOUR cases), and adds the preconditions that the case be open and, for disputes, that the caller be the opener. An agent can distinguish this from submit_evidence or open_dispute without opening any schema. It stops short of naming an alternative sibling explicitly, so it is clear but not sibling-routed.
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 constraints 'still open' and 'only whoever opened it' imply when the call is valid, but there is no explicit when-to-use vs when-not guidance (e.g., message here vs attach files via evidence_upload_link/submit_evidence). Usage is implied rather than spelled out.
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.