Skip to main content
Glama

klyo games: publish HTML5 browser games

Write the creator's profile card (owner's own AI)

klyo_creator_card
Destructive

The developer's profile card on games.klyo.pl: “about me” and the tagline under the name. YOU WRITE: the owner's assistant, on the owner's own AI plan; klyo runs no model. Without o_mnie and haslo we return the current card, the released games (the only material you may write from) and the rules. With them, we save through the same check as the studio; an omitted field stays unchanged. Saving changes the developer's public page immediately and replaces the previous text, so FIRST show the text to the owner and save only with their consent. Do not invent facts about the person.

Examples: • Write my developer profile card on klyo • Improve the tagline under my name on my developer page • What is in my profile card on games.klyo.pl now?

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hasloNoOne sentence up to 80 characters per language with no full stop; may have <pl>...</pl><en>...</en>, each version counted on its own. Keep it short: the Google title of the page is “Free {name}: {tagline}” (Polish “{nazwa} za darmo: {haslo}”) and must fit 59 characters, otherwise the page gets the generic “{name}: play free online”; do not repeat free/za darmo, the template adds it. The tool answer `do_poprawy` shows the resulting title per language. Omit to leave it as it is.
o_mnieNo“About me” in the first person; two versions in tags <pl>…</pl><en>…</en>. Omit to only read.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / haslo / description
      Previous value: -"One sentence up to 80 characters per language with no full stop; may have <pl>...</pl><en>...</en>, each version counted on its own. Omit to leave it as it is."New value: +"One sentence up to 80 characters per language with no full stop; may have <pl>...</pl><en>...</en>, each version counted on its own. Keep it short: the Google title of the page is “Free {name}: {tagline}” (Polish “{nazwa} za darmo: {haslo}”) and must fit 59 characters, otherwise the page gets the generic “{name}: play free online”; do not repeat free/za darmo, the template adds it. The tool answer `do_poprawy` shows the resulting title per language. Omit to leave it as it is."
  2. Changed2 schema fields changed
    • changedInput schema / properties / haslo / description
      Previous value: -"One sentence up to 80 characters with no full stop; may have <pl>…</pl><en>…</en>. Omit to leave it as it is."New value: +"One sentence up to 80 characters per language with no full stop; may have <pl>...</pl><en>...</en>, each version counted on its own. Omit to leave it as it is."
    • changedInput schema / properties / haslo / maxLength
      Previous value: -90New value: +400
  3. Changed2 schema fields changed
    • changedInput schema / properties / haslo / description
      Previous value: -"Jedno zdanie do 80 znaków bez kropki; może mieć <pl>…</pl><en>…</en>. Pomiń, żeby zostało, jak jest."New value: +"One sentence up to 80 characters with no full stop; may have <pl>…</pl><en>…</en>. Omit to leave it as it is."
    • changedInput schema / properties / o_mnie / description
      Previous value: -"„O mnie” w pierwszej osobie; dwie wersje w znacznikach <pl>…</pl><en>…</en>. Pomiń, żeby tylko odczytać."New value: +"“About me” in the first person; two versions in tags <pl>…</pl><en>…</en>. Omit to only read."
  4. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the destructiveHint/idempotentHint annotations, it discloses that saving immediately changes the public page and replaces previous text, that an omitted field stays unchanged, that writes pass the same check as the studio, and that klyo itself runs no model (the owner's AI plan does the writing). This is exactly the extra behavioral context annotations cannot carry.

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 read/write contract is front-loaded and every clause carries information, but the all-caps 'YOU WRITE' framing and some doubled phrasing ('we save through the same check as the studio') make it denser than needed. The trailing examples are useful routing aids.

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, the description still tells the agent what a read returns (current card, released games, rules) and what the answer exposes (do_poprawy). Combined with the consent requirement and the omission semantics, an agent has everything needed to call this mutation correctly.

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% with very rich per-parameter text, so the baseline is 3. The description adds meaning the schema does not: that both parameters are optional and their presence/absence switches the tool between read and write mode, and that an omitted field is left untouched.

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 names a specific verb (write) and resource (the developer's profile card on games.klyo.pl), and enumerates exactly what is written: the 'about me' text and the tagline under the name. It is clearly distinguishable from the sibling tools, none of which touch the creator profile.

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?

It states the dual mode explicitly: omitting o_mnie and haslo returns the current card, released games and rules, while supplying them saves. It also prescribes a workflow (show the text to the owner first, save only with consent) and warns not to invent facts. It does not compare against any alternative tool, but no sibling covers this surface.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.