Ask a real, manually approved developer for help. Nothing is sent until you confirm by email.
Scored across 1 tool
There is only one tool, so there is no possibility of misselection between tools. Its purpose (escalating to a human developer) is unambiguous and clearly stated.
The single name ask_human_developer follows a clear verb_noun convention and reads naturally. With one tool there is no risk of mixed conventions.
A single tool is thin in absolute terms, but the server's scope is inherently one operation: hand off to a human. Every part of the surface earns its place, with no filler tools.
The escalation lifecycle is only partially covered: an agent can create a request but cannot check its status, cancel it, or follow up on an existing request. These are notable but workable gaps given the confirmation-by-email and phone-call flow handled outside the MCP surface.
Connect the user with a real, manually approved human developer. Use it when the user asks for a human, a code review, a consultation or hands-on help, or when you have made a real attempt at their software problem and it is still not solved or is beyond what you can do reliably (unclear requirements, a risky change to production, a bug you cannot reproduce). It starts a request on humansfix.ai. A developer then calls the user for a free video call, and nothing is charged unless the user later accepts a fixed price. BEFORE calling: ask the user for permission, and for their own email address. Do not include passwords, API keys, tokens or other secrets in the summary. The request is not sent to any developer until the user confirms it with a code we email them.
| Name | Required | Description | Default |
|---|---|---|---|
| tool | No | The AI tool the app was built with, if known. | |
| Yes | The person's own email address, given by them. We send a confirmation code there. | ||
| summary | Yes | What the person needs, in plain words: what is wrong or what they want help with, what they were doing, and what has already been tried. No secrets. | |
| availability | No | When the person is free for a call, for example 'weekdays after 5pm CET'. Optional. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare it is not read-only, is open-world and not idempotent; the description adds far more: a request is created on humansfix.ai, a developer then calls for a free video call, nothing is charged unless the user accepts a fixed price, and nothing reaches a developer until the user confirms an emailed code. It also warns not to include secrets in the summary, which is meaningful operational guidance for an external-action tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the purpose, then usage conditions, then the consequences and pre-call checklist; every sentence carries operational weight. It is somewhat dense, especially the parenthetical failure examples, but the length is justified for an external, user-affecting escalation action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers the full lifecycle an agent needs: when to escalate, what to ask the user first, what happens after submission, and pricing/consent safeguards. The only gap is that it does not say what the call returns (for example a request id or status), which matters slightly since there is no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents all four fields and sets the baseline at 3. The description adds genuine constraint meaning beyond the schema: the email must be the user's own and is used for a confirmation code, and the summary must not contain passwords, API keys, or tokens.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a concrete verb and outcome: connect the user with a real, manually approved human developer, and notes the request is created on humansfix.ai. An agent can immediately tell this is an escalation-to-human action rather than a code or lookup tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly enumerates trigger conditions (user asks for a human, code review, consultation, hands-on help) and the fallback condition after a genuine attempt fails, with concrete examples such as unclear requirements, risky production changes, and unreproducible bugs. It also states the pre-call requirements: ask permission and obtain the user's own email.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
ask_human_developerFree check by an AI agent on your live app. On request: independent code review, fix, live re-check.
Ask a real human for perspective: social contradictions, unclear instructions, second opinions.
Let your AI agent hire a human for tasks it can't do — first post free.
Give any AI agent a way to ask a person — for approval, a decision, an answer or a review.
Add one secure layer between your agents and this server.