KI Tools Heute

Submit a new AI tool

submit_tool

Submit a new AI tool to KI Tools Heute on behalf of its maker. Creates a draft listing (not yet public) and returns a claimUrl the maker must visit to sign up and claim/publish it. Call this only when a user explicitly wants to list their own tool — never to submit a tool on someone else's behalf without their email. Rate-limited globally to 5 submissions per hour. Supply tagline, problemSolved, logoUrl and imageUrls whenever you can: they are what make the published listing look like a real product page rather than a stub.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	The tool's https homepage URL.
`name`	Yes	The tool's name.
`email`	Yes	The maker's email — used to claim the listing on signup.
`logoUrl`	No	https URL of the tool's logo. We copy it to our own storage — we never hotlink the maker's host.
`tagline`	No	One line shown on every card (max 60 chars). Supply it — without one we fall back to a truncated description.
`xHandle`	No	X/Twitter handle, without the @.
`category`	Yes	Category slug, e.g. 'agents', 'writing', 'coding', 'design', 'marketing', 'productivity', 'video', 'analytics'.
`imageUrls`	No	Up to 5 https screenshot URLs, best first. Copied to our own storage. Without any, the listing shows a generated placeholder card instead of a real screenshot.
`description`	Yes	A description of the tool (40-1000 chars).
`problemSolved`	No	What problem the tool solves, in the maker's words (max 160 chars). Rendered as its own block on the listing page.
`xHandleIsFounder`	No	True when the handle is the founder's personal account rather than the product's.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes
`error`	No
`claimUrl`	No	Where the maker signs up to claim the DRAFT. Present only when ok is true.

TDQS

A4.9/5.0

Behavior5/5

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

The description discloses that the submission is not immediately public, requires a claimUrl visit for publishing, and is rate-limited globally to 5 per hour. These behaviors are not covered by annotations (which only say readOnlyHint=false, etc.), adding critical context beyond structured metadata.

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?

The description is concise, with each sentence adding distinct value: purpose, behavior, usage caveat, rate limit, and parameter guidance. No filler or repetition of schema details.

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?

Given the complexity (11 params, 5 required) and the provided output schema, the description covers purpose, workflow, caveats, and parameter guidance sufficiently. The schema covers parameter formats, and the description fills in behavioral and contextual gaps, resulting in a complete picture.

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?

Although schema coverage is 100%, the description adds meaning for parameters like tagline, problemSolved, logoUrl, and imageUrls, explaining their impact on listing quality. It complements the schema without redundancy, adding value by motivating supply of these fields.

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 clearly states the tool submits a new AI tool on behalf of its maker, with a specific outcome: creates a draft listing and returns a claimUrl. It clearly distinguishes from siblings like get_tool and search_tools by focusing on submission, not retrieval.

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?

The description explicitly states when to use: only when a user wants to list their own tool, and warns against submitting on someone else's behalf without their email. This provides clear usage guidance and exclusions, distinguishing it from other tools like create_checkout.

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

All KI Tools Heute tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0

Disambiguation5/5

Each tool targets a clearly distinct action: searching, retrieving details, finding alternatives, listing offers, creating a checkout, and submitting a tool. Though search_tools and list_alternatives both return catalog entries, their triggers and inputs are sufficiently different that an agent can reliably choose correctly.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern: create_, get_, list_, list_, search_, submit_. The only variation is singular vs plural nouns, but the verb pattern is uniform and predictable enough that the toolset reads as one coherent convention.

Tool Count5/5

Six tools is a well-scoped size for a directory-plus-purchase workflow. Each tool covers a distinct step in the user journey, from discovery to submission to paid add-on checkout, without redundant bloat or a frustratingly thin surface.

Completeness4/5

The core workflows—search, detail retrieval, alternatives, listing creation, offer inspection, and checkout generation—are present and connect together without dead ends. However, there is no way to update, delete, or paginate through tool listings, and search_tools caps at 20 results, which is a minor gap for a full lifecycle.

Resources

Need Help?