YouGame

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

Annotations already mark this as read-only and idempotent, and the description adds substantial behavioral context: the exact verdict categories, the 8 MB text scanning limit, the requirement to pass all file paths with relative forward-slash paths, and the iterative 'fix and rerun' workflow. It also explains the meaning of 'broken' ('the game will not start'). No contradiction with annotations.

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?

Three sentences, each earning its place: purpose/verdict, input preparation rules, and post-check workflow. It is front-loaded with the main verb and result, and contains 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.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description fully explains the return value (verdict types) and provides all necessary input constraints and the recommended follow-up action. For a pre-upload validation tool, this is complete enough for an agent to invoke it correctly and interpret the result.

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?

Though schema coverage is 100%, the description adds critical parameter semantics: 'every file path in the folder', 'relative to the folder, forward slashes', which files need text (index.html plus .html/.css/.js files), and the 8 MB total text cap. This meaningfully extends what the schema alone provides, helping the agent construct the `files` array correctly.

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 action ('Runs YouGame's pre-upload checks'), a specific target ('build folder'), and a clear output ('verdict: ready, risky, or broken'). This clearly distinguishes it from siblings like publish_game, fetch, or search by defining exactly what it checks and what it returns.

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 gives workflow context: run it before upload, fix reported issues, rerun until ready, then zip and upload. It does not explicitly name alternative tools or say when not to use it, but the pre-upload placement and 'until the verdict is ready' instruction make the usage window clear.

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 establish the read-only, idempotent, non-destructive nature of the tool. The description adds useful behavioral context by specifying that the full text of the section is returned and that the id comes from a prior search, which supplements the annotation coverage without contradicting it.

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 a single, well-structured sentence with no filler. It front-loads the action and outcome, then specifies the input format and provenance, making every part informative.

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 simple one-parameter read-only tool with no output schema, the description is complete: it states what is returned, what input is needed, and where that input comes from. No critical information is missing for correct invocation.

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 100%, so the parameter is already well documented in the schema. The description reinforces that the id is a section id from search and gives an example, but it does not add significant meaning beyond what the schema provides.

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 clearly states a specific verb ('Returns') and resource ('full text of one YouGame documentation section'), and it specifies the input is the id returned by search. It is distinct from the search tool, but it does not explicitly name or differentiate itself from content-related siblings like get_sdk_reference or get_publish_guide.

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 phrase 'by the id search returned' provides clear workflow context, implying this tool should be used after search and to retrieve a specific section. However, it does not explicitly state when not to use it or mention alternatives, so it stops short of full guidance.

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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is established. The description adds useful context about what content the guide covers, including build layout, paths, limits, the runtime sandbox, common failures, and verification/upload steps, without contradicting the annotations.

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 two sentences with no filler. The first sentence front-loads the core content and the second sentence provides the direct usage instruction, making efficient use of every word.

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 parameterless read-only guide tool, the description provides sufficient context: what the guide covers, why an agent would need it, and when to read it. There is no output schema or complex behavior that would require additional explanation.

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?

The tool has zero parameters, so there is no parameter schema for the description to supplement. The baseline of 4 applies here, and the description appropriately focuses on what the returned guide contains rather than parameter details that do not exist.

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 clearly states that this tool retrieves the rules and verification steps for making a browser game YouGame-ready, with a specific resource ('publish guide') and content areas. It is distinct from siblings like check_build or publish_game by its focus on rules and how-to guidance, though it doesn't explicitly name alternatives.

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 phrase 'Read this first when making a game YouGame-ready' gives an explicit usage context and priority. It does not mention when to use alternative sibling tools instead, but the 'read this first' instruction is clear enough to guide an agent toward this tool at the start of the workflow.

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 the tool as read-only, idempotent, and non-destructive. The description adds useful behavioral context beyond those annotations by noting that integration requires 'One script tag' and 'no account needed,' which helps an agent understand access and setup expectations.

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 a single, front-loaded sentence that immediately states what the tool is, then compresses the scope and setup into an efficient list. Every clause adds information, with no redundancy or filler.

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 zero-parameter reference tool, the description adequately covers what the reference includes and key access characteristics. It could be slightly more complete by mentioning the form of the returned reference, but the current content is sufficient for an agent to select and invoke it correctly.

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?

The tool accepts zero parameters, and the schema fully reflects this with an empty properties object. The description has no parameter semantics to explain, and the feature list provides the relevant selection context, so the baseline for a zero-parameter tool applies.

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 explicitly identifies the resource as 'the complete YouGame SDK reference' and enumerates covered areas (leaderboards, multiplayer, matchmaking, friend invites, skill ratings, coins). This clearly distinguishes it from sibling tools like get_publish_guide, which focuses on a different reference topic.

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 implies use when an agent needs SDK integration information and lists the topics it covers. However, it does not explicitly state when to choose this over alternatives such as get_publish_guide or search, so the routing guidance is only implicit.

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 the tool as read-only, idempotent, and non-destructive. The description adds the auth need ('Needs the creator's API key'), and the parameter schema supplies additional context that passing the key in the call exposes it in transcripts/logs. This goes beyond the annotations and gives the agent important safety-relevant behavior.

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?

Two concise sentences with no filler. The first sentence front-loads the core purpose and return fields; the second states the auth requirement. It is efficient, though starting with an imperative verb would improve structure.

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 simple read-only list tool with just one optional parameter, the definition is nearly complete. It lists the returned fields, compensating for the lack of an output schema, and the schema provides strong parameter guidance. The main gaps are the absence of pagination/ordering details and sibling differentiation, but these are not critical for basic invocation.

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 100%, and the api_key parameter is extremely well documented in the schema: when to send it, how to avoid it, and the security implications. The tool description itself only says the creator's key is needed, which adds little beyond the schema. Baseline 3 is appropriate.

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 clearly identifies the resource (the games the API key creator has published on YouGame) and enumerates the returned fields (slug, URL, title, version, plays, SDK features). It is not a tautology and the scope is understandable. It loses a point because it uses a noun phrase rather than an imperative verb and does not explicitly distinguish itself from sibling tools like 'search'.

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?

There is no guidance on when to choose this tool versus alternatives such as 'search' or 'update_game'. The only usage-related statement, 'Needs the creator's API key,' is an authentication prerequisite rather than a decision rule for tool selection.

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?

The annotations (idempotentHint=true, destructiveHint=false) are consistent, and the description richly extends them: it discloses that the tool only saves a draft ('nothing is live until they do'), that it requires the creator's API key, that it has a hard precondition on a prior upload step, and that it is safe to call repeatedly with revised answers. The behavioral context goes well beyond what the annotations alone convey.

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 long (~300 words), but the length is earned by the tool's complexity: a preconditioned workflow, an external curl command with exact endpoint and headers, an ask-before-call protocol, and a safety guarantee. The purpose is front-loaded in the first sentence and the workflow proceeds sequentially. The curl example is verbose but operationally necessary since the endpoint is external; still, it could have been trimmed by pointing to the API reference.

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 14-parameter, 8-required tool with no output schema, the description covers everything an agent needs: the staging precondition with exact commands, how to handle a broken verdict, which fields to decide vs. ask about, the re-call loop for the reply's questions, the review-link return value, and the publish safety gate. Nothing an agent would need to call this tool correctly 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 coverage is 100%, so the baseline is 3, but the description adds value the schema cannot: it explains the provenance of uploadId ('From the upload reply'), groups the parameters by decision source ('decided from what you know about the game' vs 'ask the creator first'), and clarifies the cross-parameter workflow (what to ask about before calling, what to do with the reply's questions). This is meaningful additive guidance beyond the per-property schema descriptions.

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 first sentence states a specific verb and resource: 'Fills in the whole YouGame listing of a staged build and saves it as a draft for the creator to review.' It is unambiguous about the tool's role in the publishing flow and explicitly distinguishes itself from publish_game ('Never call publish_game instead of handing over the link'), so an agent can tell it apart from its siblings 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.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives an explicit when-to-use workflow: stage the build with a curl command, check the upload verdict, call this tool, ask the creator about undecidable fields, re-call with answers, and hand over the review link. It also names the exclusion condition for the sibling publish_game ('unless the creator explicitly asked you to publish without reviewing'). This is textbook usage guidance.

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?

Beyond the annotations (mutation, idempotent, non-destructive), the description discloses the consequential behaviors: the game goes live immediately and bypasses the human review gate, the tool refuses without explicit creator consent, and passing api_key in the payload 'ends up in the agent's transcript and tool logs.' These are materially useful behavioral disclosures that annotations alone do not convey, and nothing contradicts the idempotentHint.

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?

Five sentences, all front-loaded: the action and its most important consequence come first, then the alternative path, then the strict consent condition, then the parameter shortcut. No filler; even 'never because it is faster' earns its place as a guard against anticipated misuse.

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 safety-sensitive 14-parameter mutation that goes live publicly, the description covers the decision boundary, the consent requirement, and the parameter shortcut, while the fully documented schema handles field semantics and defaults. The only real omission is the return value or confirmation shape, which is minor because the tool's risk profile and invocation rules are completely specified.

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 baseline is 3; the description adds genuinely new inter-parameter semantics: 'After prepare_submission the uploadId alone is enough (every other field keeps the draft's value); otherwise pass the listing fields.' That relationship — when one required field suffices versus when the whole listing must be passed — is nowhere in the per-field schema and materially changes how the agent fills the call.

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?

Opens with a specific verb and resource — 'Publishes a staged build as a game on YouGame' — and immediately adds the distinguishing consequence 'live at once, skipping the creator's review.' That phrase sets it apart from the sibling prepare_submission, which hands the creator a review link, so the agent can tell the two apart from the first sentence alone.

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?

Names the alternative explicitly: 'the normal path is prepare_submission, which hands the creator a review link where they press Publish themselves.' It then states a strict when-to-use rule — only when the creator said, in their own words, to publish without the review page — reinforced by a counter-example ('looks good' about a draft is not that) and a standing prohibition ('never because it is faster').

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 establish readOnlyHint, idempotentHint, and destructiveHint=false, so no safety disclosure is needed. The description adds behavioral context by naming the exact document set and the output shape (matching sections with ids), and explicitly defines the follow-up fetch call.

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?

Two sentences with no filler. The first sentence is front-loaded with action, scope, and result; the second provides usage criteria and a concrete follow-up instruction.

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 one-parameter, read-only search tool, the description covers the search scope, the output format, when to use it, and the next action. No output schema exists, but 'matching sections with ids' is sufficient for an agent to use the results correctly.

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?

The schema covers the single query parameter 100%, so the baseline is 3. The description adds value by giving natural-language question examples ('how scores are posted, what multiplayer guarantees, what breaks a build') and clarifying that the query should represent a specific question, which helps the agent formulate effective queries.

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 ('Searches'), a precise resource ('the YouGame documentation (the publish guide and the SDK reference)'), and the output ('returns matching sections with ids'). It clearly distinguishes the tool from sibling document readers like get_publish_guide or get_sdk_reference by framing it as targeted search.

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 explicitly says to use it 'to answer a specific question' and contrasts with 'without reading a whole document', implying when whole guides are needed the sibling get_* tools are appropriate. It also routes the agent to call 'fetch with an id' afterward, naming the next step.

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 declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is known. The description adds substantial context beyond that: it requires the creator's API key, preserves scores and comments, and discloses side effects — major updates notify every saver/liker and feature on the home feed for a week, minor updates are silent. No contradiction with the annotations.

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?

Longer than typical, but dense and front-loaded: the core purpose is the first clause, followed by auth, staging workflow, and kind semantics in a logical sequence. Each sentence earns its place for a workflow-heavy mutation tool; the duplicated endpoint mention could be trimmed, but there is no filler.

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 7-parameter mutation with no output schema and a prerequisite upload step, the description covers prerequisites (API key, staged build, valid uploadId), input provenance, kind semantics, and defaults — leaving little to guesswork. The main omission is the success/failure return shape, which is non-trivial for a workflow-oriented tool but not blocking.

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 baseline is 3. The description adds value the schema lacks: input provenance (slug from URL, uploadId from the upload reply), the real-world consequence of kind (notifications, home feed, version history), and an explicit defaulting rule. Minor gap: thumbnail/screenshots semantics remain schema-only, but that is acceptable at full coverage.

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?

Opens with a specific verb + resource: 'Ships a new build of a game the creator already published, as its next version.' It immediately differentiates from publish_game (first publication) and my_games (listing), and states what is preserved (same link, scores, comments). An agent can tell it apart from siblings without opening the schema.

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 routes the workflow: stage the build 'exactly as for publish_game', then call this tool, and names where inputs come from ('slug from my_games or its URL', 'uploadId from the upload reply'). It also gives a concrete decision rule — 'Default to minor unless the creator says the update is big' — and contrasts major vs minor effects so the agent picks the right kind.

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