Skip to main content
Glama

Sonar Connections

by com.sonarconnections
OverviewDiscussionsAdmin

Report card diagnostics

ui_card_diag
Idempotent

Used only by the interactive cards this connector draws, never to answer a question. A card view posts its own lifecycle markers here in small batches: that it mounted, which display mode and safe-area insets the host gave it, the heights it reported, whether a keyboard opened, and the outcome of the one action a person took on it. It accepts a closed vocabulary of markers and integer counts only, no free text of any kind, and it returns nothing but an acknowledgement. NOT FOR A MODEL TO CALL: it answers no question and looks nothing up. Call a data tool instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seqYesWhich batch this is for that mount, 1 to 6. Past the budget it is refused.
cardYesWhich card is speaking: menu, order, floor or storefront.
hostNoWhich surface drew this card when it is not an MCP host: "standalone" for the connector's own shop page. Omit it inside a host. Any other value refuses the batch.
eventsYesUp to 40 markers: {t, kind} plus optionally code, n, c, span, mode, w, h, top, bottom, tplEpoch. An off-vocabulary kind, an unknown key or a non-integer number refuses the whole batch.
sessionKeyYesA random id the card minted for THIS mount. Not a user id, not a device id, 6 to 24 lowercase alphanumerics.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / host
      Added value: +{
+  "description": "Which surface drew this card when it is not an MCP host: \"standalone\" for the connector's own shop page. Omit it inside a host. Any other value refuses the batch.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / events / description
      Previous value: -"Up to 40 markers: {t, kind} plus optionally code, n, c, span, mode, w, h, top, bottom. An off-vocabulary kind, an unknown key or a non-integer number refuses the whole batch."New value: +"Up to 40 markers: {t, kind} plus optionally code, n, c, span, mode, w, h, top, bottom, tplEpoch. An off-vocabulary kind, an unknown key or a non-integer number refuses the whole batch."
  3. Changed1 schema field changed
    • changedInput schema / properties / card / description
      Previous value: -"Which card is speaking: menu, order or floor."New value: +"Which card is speaking: menu, order, floor or storefront."
  4. Changed1 schema field changed
    • changedInput schema / properties / events / description
      Previous value: -"Up to 40 markers: {t, kind} plus optionally code, n, mode, w, h, top, bottom. An off-vocabulary kind, an unknown key or a non-integer number refuses the whole batch."New value: +"Up to 40 markers: {t, kind} plus optionally code, n, c, span, mode, w, h, top, bottom. An off-vocabulary kind, an unknown key or a non-integer number refuses the whole batch."
  5. Added

TDQS

A4.6/5.0
Behavior5/5

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

With annotations already declaring readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=false, the description adds valuable context: it posts telemetry in small batches, accepts a closed vocabulary of markers and integer counts only, no free text, and returns only an acknowledgement. This is rich beyond the structured fields.

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

Conciseness4/5

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

The description is front-loaded and every sentence contributes to preventing misuse, but there is some repetition: 'never to answer a question' and 'it answers no question' restate the same guardrail. Still appropriately sized for a tool that must be kept away from the model.

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

Completeness5/5

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

For a non-model-facing diagnostic tool with no output schema, the description explains what it accepts, what it returns (an acknowledgement), its constraints, and its intended caller. Annotations cover the safety profile, and the schema covers parameters, so nothing essential is missing.

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 the schema already fully documents each parameter and its constraints. The description adds only a high-level note about closed vocabulary and integer counts, which is useful but does not provide per-parameter meaning beyond the schema.

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: card views post lifecycle markers to this endpoint, and it explicitly says it is never for answering questions. It distinguishes itself from data tools by naming the correct alternative ('Call a data tool instead').

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?

It explicitly limits usage to interactive cards drawn by the connector, states the tool is 'NOT FOR A MODEL TO CALL,' and directs the agent to call a data tool instead. When-not-to-use is as clear as when-to-use.

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

All Sonar Connections 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