Skip to main content
Glama

Bernuvia

by com.bernuvia
OverviewDiscussionsAdmin

reply_to_case

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textNoYour message (1 to 10000 characters).
textoNoDEPRECATED 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).
caseIdNoId of the case (my_cases gives it).
casoIdNoDEPRECATED 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).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesAlways true: the message has been added to the case.
caseYesId of the case that was replied to.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / caseId / description
      Previous value: -"Id del caso (lo da my_cases)."New value: +"Id of the case (my_cases gives it)."
    • changedInput schema / properties / casoId / description
      Previous 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)."
    • changedInput schema / properties / text / description
      Previous value: -"Tu mensaje (1 a 10000 caracteres)."New value: +"Your message (1 to 10000 characters)."
    • changedInput schema / properties / texto / description
      Previous 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)."
    • changedOutput schema / properties / case / description
      Previous value: -"Id del caso al que se ha respondido."New value: +"Id of the case that was replied to."
    • changedOutput schema / properties / ok / description
      Previous value: -"Siempre true: el mensaje se ha añadido al caso."New value: +"Always true: the message has been added to the case."
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the operation is a text-only post, that file attachments must be handled in the browser, and that there are access restrictions (your cases, open cases, dispute-opener only). While it doesn't address side effects like notifications or irreversibility, it covers the key behavioral constraints an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, dense sentence that front-loads the action and resource, then packs in all essential restrictions. Every clause earns its place, with no filler or redundant restating of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity, an output schema exists (so return format needn't be described), and the description covers the essential input constraints and behavioral limits. It doesn't explicitly state failure behavior for closed cases or unauthorized users, but those are directly implied by 'still open' and 'YOUR cases'. Overall, an agent has enough to call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by clarifying that caseId must reference a case that belongs to the user and is still open, and that text is the plain-text message content. This helps the agent understand valid parameter values without extra lookup.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Posts a message on one of YOUR cases'. It adds precise scoping ('still open', 'on a dispute, only whoever opened it') that clearly distinguishes this from sibling tools like reply_to_review or submit_evidence. An agent can understand exactly what action this tool performs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when to use the tool: only on your own cases that are still open, and on disputes only by the opener. It also signals a limitation ('Text only: files are attached from the browser'), implying the tool is not for sending attachments. It does not explicitly name alternative tools for related actions, but the conditions are specific enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Bernuvia toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources