HopeHire

agent_step_api_extension_agent_step_post

Agent Step

Tier 4: one step of an agentic fallback loop for pages where tiers 1-3 (coded adapters, universal field matcher, batched AI field-answering) found nothing to work with. The extension sends a snapshot of every visible interactive element on the page; this returns exactly one action to take next. Never raises on a bad/failed model response - degrades to "blocked" so the client loop just stops rather than crashing the fill.

Responses:

200: Successful Response (Success Response) Content-Type: application/json

Example Response:

{
  "action": "Action"
}

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": {
      "job_context": "<job_context>",
      "elements": "<elements>",
      "step": "<step>"
    },
    "name": "agent_step_api_extension_agent_step_post"
  }
}

Input Schema

Name	Required	Description	Default
`step`	Yes
`history`	No
`elements`	Yes
`job_context`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

B3.2/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses a key behavior: it 'never raises on a bad/failed model response - degrades to blocked,' so the client loop stops safely rather than crashing. However, it omits cost/latency (it is a model call), statefulness across steps, and whether the returned action is executed or only suggested, leaving meaningful behavioral gaps.

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

Conciseness3/5

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

The core paragraph is front-loaded and earns its place, but it is padded with boilerplate '### Responses' and example JSON ('action': 'Action') that add little. Reasonably sized overall but with low-value tail sections.

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

Completeness2/5

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

For a complex tool with 4 params, deep nested objects, no output schema, and 0% schema coverage, the description explains the loop concept but not the inputs an agent must construct (job_context, history, step). An agent still cannot confidently assemble a request from this alone.

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

Parameters2/5

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

Schema coverage is 0% across four parameters including two nested object types (elements, job_context, history). The description only loosely gestures at 'elements' (a snapshot of interactive elements) and the returned action; it says nothing about job_context, step, or history semantics. With such low schema coverage this is a significant documentation gap.

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 role: 'one step of an agentic fallback loop' that 'returns exactly one action to take next.' It also distinguishes itself from tiers 1-3 (coded adapters, universal field matcher, batched AI field-answering), so an agent can tell it is the last-resort tier rather than the primary filler.

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?

Explicitly scopes usage: only for pages where tiers 1-3 'found nothing to work with.' This is a clear when-to-use condition and implies a when-not (don't call it if higher tiers succeed). It doesn't name a specific sibling tool as the preferred path by exact name, keeping it just under 5.

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

All HopeHire 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?