Fetch Hive

Publish an agent as a share page

share_agent

Make a public chat link for an agent, the Share button in the agent editor: anyone with the link can chat with a frozen copy of the agent (a few messages per visitor, monthly limits apply), billed to this account. One page per agent; change it later with update_share. Agents that use connected accounts, knowledge bases, MCP servers, sub-agents, workflows or a personal model key cannot be shared; the call says which. Call it first without approved: it checks the agent and returns the page copy it would publish (pass draft_copy: true to have the copy written for you). Show the person, then call again with approved: true and the copy they agreed to.

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": {
      "agent_id": "<agent_id>"
    },
    "name": "share_agent"
  }
}

Input Schema

Name	Required	Description
`copy`	No	What visitors see on the agent's page. All five text fields are required unless draft_copy is true.
`agent_id`	Yes	The agent to share.
`approved`	No	true only after the person has agreed to publish this page.
`campaign`	No	The Campaign tag (e.g. GRO-264). Private: visitors never see it.
`draft_copy`	No	Draft any copy fields you left out. Default false.
`customer_label`	No	The Customer label tag (e.g. the lead's company). Private: visitors never see it.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only flag the call as a non-read-only, open-world, non-idempotent write; the description supplies the substantive behavior they omit: a frozen copy of the agent is published, visitors can chat with rate limits per visitor and per month, usage is billed to this account, and there is one page per agent. It also discloses that ineligible agents fail at call time with the reason, which is exactly the failure mode an agent needs to anticipate.

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 purpose is front-loaded in the first clause and no sentence is filler, but the whole thing is one long run-on paragraph mixing behavior, exclusions, and the approval workflow. Splitting the two-step protocol and the eligibility limits into separate sentences would scan faster without losing content.

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?

With no output schema and six parameters including a nested object, the description still covers what the first call returns (the page copy it would publish or the blocking reason), the billing and rate-limit consequences, and the sequencing. Nothing an agent needs before invoking it is missing.

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?

Schema coverage is 100%, so the baseline would be 3, but the description adds real meaning about the gating parameters: approved is required only after the person agrees, and draft_copy: true lets the tool fill missing copy fields. The copy object itself is left to the schema, which already documents each field and the all-required-unless-draft_copy rule.

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?

Opens with a specific verb and resource ("Make a public chat link for an agent") and anchors it to a UI affordance ("the Share button in the agent editor"). It distinguishes itself from update_share by naming that sibling for later edits, so an agent can route without opening either schema.

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 an explicit two-step protocol: call first without approved to validate and get the page copy, show the person, then call again with approved: true. It also states the exclusion conditions (connected accounts, knowledge bases, MCP servers, sub-agents, workflows, personal model key) and that update_share is the tool for subsequent changes.

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

All Fetch Hive tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?