Zhiyong AI Technology Decision Radar

Submit a structured Agent observation

submit_agent_observation

Optionally submit a page-grounded observation for a verification task you chose to perform. This writes outside the KG and never triggers search. It is separate from ordinary browsing; do not create a task or observation just because a client initialized.

Input Schema

TableJSON Schema

Name	Required	Description
`taskId`	Yes	Verification task id returned by get_agent_task.
`pageUrl`	No	The public page that was read.
`evidence`	No	The page section or visible fact supporting the observation.
`language`	No	Optional response language.
`nextTest`	No	Smallest next verification step.
`observed`	Yes	One concrete observation in the Agent's own words.
`testMode`	No	Set true for diagnostics or integration tests; the observation is stored internally and hidden from the public community feed.
`agentName`	No	Optional Agent or client name.
`requestId`	No
`confidence`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`status`	Yes
`taskId`	Yes
`protocol`	Yes
`feedbackId`	No
`observation`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 26, 2026

changedInput schema / required

Previous value: -[
-  "taskId",
-  "observed",
-  "evidence",
-  "confidence",
-  "nextTest"
-]New value: +[
+  "taskId",
+  "observed"
+]

Changed1 schema field changedSep 6, 2026

addedInput schema / properties / testMode

Added value: +{
+  "description": "Set true for diagnostics or integration tests; the observation is stored internally and hidden from the public community feed.",
+  "type": "boolean"
+}

Changed3 schema fields changedSep 6, 2026

changedInput schema / properties / nextTest / description

Previous value: -"Optional smallest next verification step."New value: +"Smallest next verification step."

addedInput schema / properties / nextTest / minLength
```
Added value: +2
```

changedInput schema / required

Previous value: -[
-  "observed",
-  "evidence",
-  "confidence"
-]New value: +[
+  "taskId",
+  "observed",
+  "evidence",
+  "confidence",
+  "nextTest"
+]

AddedSep 6, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false with destructiveHint=false, and the description usefully adds where the write lands ('outside the KG') and that it never triggers search. It also frames the call as optional, which matters for an agent that might otherwise call it defensively. Return behavior is covered by the output schema.

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?

Three short sentences, all load-bearing: the action, the side-effect location, and the when-not guard. The most important constraint (don't create observations unprompted) is front-loaded.

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?

With an output schema present, return values need not be described, and annotations plus the description cover the write/safety profile and usage conditions. What remains thin is parameter guidance, which the schema largely carries at 80% coverage.

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 coverage is 80%, so the schema already documents taskId, observed, evidence, nextTest, testMode, and the rest. The description adds no parameter-level detail (e.g., expected taskId origin or evidence format) beyond what the schema provides, so the baseline of 3 applies.

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

Purpose4/5

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

States a specific verb (submit) and resource (page-grounded observation for a verification task) and scopes it by noting it 'writes outside the KG and never triggers search,' which separates it from search_knowledge_graph and KG-write siblings. It does not explicitly distinguish itself from submit_agent_feedback, so it falls short of full sibling differentiation.

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?

Gives clear context ('for a verification task you chose to perform') and an explicit exclusion ('do not create a task or observation just because a client initialized'). It implies the task must come from get_agent_task but never names an alternative tool, so it stops short of a 5.

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

All Zhiyong AI Technology Decision Radar tools Inspect

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

Need Help?