Skip to main content
Glama

Glasser

by ai.glasser
OverviewDiscussionsAdmin

Inspect endpoint

inspect
Read-only

Get one endpoint's execution contract: provider-native input schema, exact price with every charge clause, current endpoint_version, run mode and timeout. Always inspect before the first run of an endpoint, and pass the endpoint_version you saw to run. Selecting an endpoint_version does not lock Price; new Runs use the current Price at admission. Pass the task_id from your search so this inspection is recorded against the same piece of work. Docs: https://glasser.ai/docs/api-reference/endpoints/inspect

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
task_idNo
endpointYes
providerYes
endpoint_versionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / task_id / anyOf
      Previous value: -[
-  {
-    "description": "The task this call belongs to. Omit on the first search of a piece of work and one is minted and returned; pass it back on every later search, inspect and run so they are recorded as one task. Any stable string is accepted.",
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "description": "The task this inspection belongs to, from a catalog search response. Any stable string is accepted.",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
  2. Changed1 schema field changed
    • addedInput schema / properties / task_id
      Added value: +{
+  "anyOf": [
+    {
+      "description": "The task this call belongs to. Omit on the first search of a piece of work and one is minted and returned; pass it back on every later search, inspect and run so they are recorded as one task. Any stable string is accepted.",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}
  3. First observed

TDQS

A4.3/5.0
Behavior4/5

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

The readOnlyHint and destructiveHint annotations already establish that this is a safe, non-destructive operation. The description adds valuable behavioral nuance beyond annotations: selecting an endpoint_version does not lock Price, new Runs use the current Price at admission, and task_id is used to record the inspection against the same piece of work.

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 compact and front-loaded: the first sentence states the core contract, and the following sentences add necessary workflow and pricing caveats. The docs URL is a minor addition but not wasteful.

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?

The description provides enough context for a read-only pre-run inspection tool: it says when to call it, what it returns, and how it relates to run and search. There is no output schema, so its explicit enumeration of returned fields helps. A concrete example or error behavior would improve completeness slightly.

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?

With schema description coverage at 0%, the description must compensate, and it does for the two non-obvious parameters: task_id should come from a search and is used for recording, and endpoint_version can be selected without locking price. It does not explain provider and endpoint formats, but their schema patterns and names are largely self-explanatory.

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 names a specific verb ('Get') and a precise resource ('one endpoint's execution contract') and enumerates exactly what is returned: provider-native input schema, exact price with charge clauses, endpoint_version, run mode, and timeout. This clearly distinguishes inspect from sibling tools like run or search.

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 an explicit when-to-use rule: 'Always inspect before the first run of an endpoint.' It also connects to sibling tools by instructing the agent to pass endpoint_version to run and task_id from search. It does not explicitly state when not to use the tool, but the guidance is strongly contextual.

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

All Glasser 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