publish

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

The description adds substantial behavior beyond the annotations: no account or API key required, a 2.5 MB total file limit, required top-level index.html, the 7-day claim requirement or disablement, and the iframe embedding/16:9 layout caveat. This gives the agent practical expectations about the call's side effects and constraints.

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?

The description is front-loaded with the core purpose and selection guidance, then flows into constraints, return values, sibling routing, and build-time advice. It is long but every sentence carries distinct, useful information; the final clarification that the framing advice is not a publishing requirement prevents over-caution without adding fluff.

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?

For a publish tool with one required parameter and an output schema, the description provides everything needed to select and invoke it correctly: input requirements, size limits, output fields, post-publish ownership behavior, and the update path. Nothing critical is missing.

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 description coverage is high at 86%, so the baseline is 3. The description adds value by surfacing aggregate constraints not in the schema, such as the 2.5 MB total file size limit and the practical impacts of the optional cover image, while the schema already documents the individual parameters well.

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?

The description states a precise verb and resource: 'Publish a browser game (HTML5/JavaScript, static files) to Playfrog and get a public, shareable play link.' It also explicitly names the sibling, update_game, as the way to publish later versions, so the tool is clearly differentiated from it.

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?

It says directly, 'This is the tool to use whenever someone wants to publish, share, post, put online, put on the internet, or host a browser game,' giving a strong selection signal. It also routes update scenarios to update_game with the needed game_id and manage_token, naming the alternative and the condition for using it.

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

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

Annotations already mark destructiveHint=true and readOnlyHint=false, but the description adds meaningful context beyond that: it replaces the entire game (complete file set required), preserves the play URL, and returns a new version_id. This clarifies the mutation semantics and aligns with the destructive hint without contradiction.

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?

The description is five sentences, each contributing distinct information: purpose, when to use, required tokens, file handling, and return values. It is front-loaded with the core purpose and contains no filler. Slightly longer than necessary but well-structured.

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?

Given the tool's complexity (10 params, nested objects) and an existing output schema, the description covers the essential context: when to use, prerequisites, how to provide files, and what to expect (new version_id, same play_url). It does not cover error conditions, but these are typically beyond description scope, and the schema handles parameter details.

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 description coverage is 90% (high), so the baseline is 3. The description adds value by noting that game_id and manage_token come from the publish_game response, which clarifies their provenance. It does not elaborate on other parameters, but the schema already covers them thoroughly, so it does not need to compensate.

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?

The description states a specific verb ('Publish a new version') and a specific resource ('an existing Playfrog game'), and explicitly distinguishes it from the sibling publish_game by emphasizing 'existing' and 'at the same play link'. This makes the tool's purpose unambiguous and clearly differentiates it.

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?

The description explicitly says 'Use this when the user wants to update, change, replace, or re-publish a game already on Playfrog', which gives clear invocation conditions. It also cautions to 'Send the complete set of files again, not a diff', a key usage tip. It implies the alternative (publish_game for new games) by requiring tokens from publish_game, though it does not explicitly state 'use publish_game for new games'.

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