Skip to main content
Glama

Tell Audora what you could not do

report_gap

Call this whenever the artist asks for something there is no tool for, or a tool refuses in a way you cannot work around. It files the ask in Audora's support inbox, where a person reads it, and it shows in the artist's Settings › Support. Call it before you tell the artist no. It changes nothing in their catalog, and it is the only way the ask reaches anyone.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "asked_for": "<asked_for>"
    },
    "name": "report_gap"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoAnything that would help Audora understand the ask.
asked_forYesWhat the artist wanted, in their own words as far as you can keep them.
tool_triedNoThe tool you tried or looked for, if there was one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations say readOnlyHint=false while destructiveHint=false; the description reconciles this by stating the write lands in a support inbox and 'changes nothing in their catalog', which is genuinely useful context beyond the flags. It also discloses human review and the Settings › Support visibility. The one gap is duplicate behavior — idempotentHint=false means repeated calls likely create multiple tickets, but the description never warns against re-reporting the same gap.

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?

Four short sentences, front-loaded with the trigger, then the effect, then the ordering constraint. Every clause carries routing or safety information; nothing is restated from the title or schema.

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?

For a simple 3-parameter reporting tool with annotations present and no output schema, the description covers trigger, destination, visibility, and non-impact on the catalog — enough to call it correctly. It stops short of describing what comes back after filing (e.g., a confirmation or ticket reference), which would help an agent tell the artist what happens next.

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

Parameters3/5

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

Schema description coverage is 100%, so all three fields (asked_for, note, tool_tried) are already documented. The description only indirectly reinforces asked_for via 'in their own words as far as you can keep them' phrasing, but gives no added guidance on what belongs in note versus tool_tried. Baseline 3 applies.

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?

States a concrete action (file the ask in Audora's support inbox) plus its audience (a person reads it) and its visible surface (Settings › Support). The trigger condition — 'no tool for it, or a tool refuses in a way you cannot work around' — makes it unmistakable against every sibling, none of which routes requests to support.

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

Usage Guidelines5/5

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

Gives both an inclusion rule and a timing rule: call it when no tool exists or a blocked tool cannot be worked around, and 'call it before you tell the artist no'. That is an explicit when-to-use plus an ordering constraint relative to the artist-facing refusal, leaving little to infer.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources