Playable Gift

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

Annotations already declare readOnlyHint=false, idempotentHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description goes further by translating idempotentHint into concrete behavior ('repeated requests with the same idempotency key return the existing draft') and by disclosing return values (preview URL, private management token) and content prohibitions. It stops short of permission/auth requirements and whether drafts can later be deleted or published.

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, front-loaded with purpose then return values, then constraints. Each sentence carries distinct information (outcome, outputs, acceptance rules, prohibitions, idempotency) with no obvious filler, though the acceptance-criteria list is dense enough to be hard to scan.

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?

With no output schema, the description usefully documents the return shape, and it covers content rules and idempotency. But for a ten-parameter, one-nested-object tool, the absence of any explanation for the people/metadata parameters (sender, recipient, occasion, theme, message) is a real completeness gap an agent would notice when filling the required fields.

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?

Top-level schema description coverage is 0%, so the description must carry parameter meaning. It does well for the game payload and idempotencyKey, but eight of ten parameters (recipient, sender, title, concept, message, occasion, theme, recipientEmail) receive no explanation at all in either field. Critically, it never clarifies whether recipientEmail triggers an actual send or is merely stored, despite the tool being a 'draft'.

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 and resource ('Saves a supplied self-contained HTML game') and the resulting artifact ('as a free private draft'), plus what is returned. It is clear, but it never differentiates itself from the adjacent write tools in the sibling list (make_game, revise_custom_game), leaving the agent to guess which save/create path applies.

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?

Usage is implied through the acceptance criteria ('accepted games have inline code...') and the idempotency contract, so an agent can infer what input is valid. However, there is no explicit when-to-use guidance and no routing versus make_game, revise_custom_game, or export_gift, which is the main decision an agent faces here.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the bar is lower, yet the description adds genuinely useful context: output is portable JSON with self-contained HTML, and the recipient's email address and private tokens are deliberately excluded. That redaction detail is not derivable from annotations or schema.

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 short sentences, zero filler, and the payload/return shape is front-loaded before the redaction note and the optional parameter. Every sentence carries distinct information.

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?

With no output schema, the description does the job of characterizing the return value (portable JSON with self-contained HTML) and the redaction behavior. The only gap is that it never explains the required managementToken or where it comes from, which matters for a private-draft export.

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 50%: revision is documented in the schema and the description only mildly extends it (retained vs. current revision), while managementToken has no description anywhere. Baseline 3 is appropriate since the description adds marginal value but does not compensate for the undocumented required auth parameter.

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 specific verb and resource: 'Returns a private draft as portable JSON containing its complete self-contained game HTML.' The 'private draft'/'portable JSON' framing distinguishes it from sibling get_gift and get_gift_history, but no sibling is named explicitly, so the differentiation is implicit.

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?

No when-to-use or when-not-to-use guidance. The only conditional sentence concerns the revision parameter ('selects a retained revision instead of the current version'), which is parameter behavior, not task routing. An agent must infer from the name alone when to pick this over get_gift or get_made_game.

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 read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuine behavioral value by disclosing the exact payload (metadata, revision, preview link, status) and, importantly, that 'Game HTML is excluded' — a negative disclosure that prevents a wrong expectation.

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 tight sentences with no filler. The return payload is front-loaded and the exclusion clause follows immediately, so nothing is buried.

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?

With no output schema, the description correctly enumerates the returned fields, and annotations cover the safety profile. Minor gaps remain around error behavior for an invalid/unknown token and the token's expected format, but an agent has enough to 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?

There is one parameter with 0% schema description coverage, so the description must carry the burden. It identifies the input as a 'management token' and frames it as the identifier of the draft being read, but gives no format, sourcing, or validation detail beyond that.

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 gives a specific verb-plus-resource ('Returns a private draft's metadata') and enumerates the returned fields, which resolves the ambiguity between the tool name 'get_gift' and its title 'Read a draft'. It does not explicitly differentiate itself from siblings such as get_made_game or export_gift, which share the draft-reading space.

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 'for the supplied management token' hints at a prerequisite, but there is no explicit statement of when to use this tool versus alternatives like get_made_game or export_gift, and no exclusions. The agent is left to infer routing from the tool name alone.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds useful content-level context, telling the agent this is a static rules/capability reference rather than instance data, but it discloses nothing about auth needs, limits enforcement, or freshness of the returned rules.

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?

A single front-loaded sentence that begins with the verb 'Returns' and enumerates the payload concisely, with no filler. It could be marginally tighter, but every clause carries meaning.

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?

No output schema exists, so the description must characterize the return value, and it does enumerate the categories of content returned. Combined with full annotation coverage and zero parameters, this is nearly sufficient for calling the tool, though it never resolves the naming ambiguity between 'gift catalog' and 'custom game rules'.

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 takes zero parameters, so there is nothing for the description to document beyond what the empty schema shows. Baseline 4 applies; the description correctly implies a no-argument catalog read.

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 names a concrete return payload ('formats, capabilities, requirements and limits') and a scope ('saving custom HTML games as private drafts'), which is more than a restatement. However, it never reconciles itself with the tool name get_gift_catalog and the title 'Read custom game rules', so an agent cannot tell whether 'gift catalog' and 'custom game rules' are the same artifact. The purpose is inferable but the resource identity is muddled.

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 when-to-use guidance, no prerequisites, and no reference to any alternative. With siblings like create_custom_game, revise_custom_game, and make_game available, the description should say this is the read-only prerequisite lookup before writing a draft, but it does not.

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 readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value beyond them: a hard five-revision retention limit, a PII warning ('may contain the sender's personal content'), and an explicit data exclusion ('Game HTML is excluded'). It stops short of describing failure modes for an invalid or expired token.

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 tight sentences that are front-loaded with what is returned, then the retention limit, then data caveats. Every sentence carries information an agent cannot get from the schema or annotations.

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?

With no output schema, the description must convey the return shape, and it does so reasonably: last five revisions, revision metadata contents, and excluded HTML. Safety and idempotency are covered by annotations, so the main residual gap is error/permission behavior for an invalid token.

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?

There is one parameter with 0% schema description coverage, so the description carries the burden. It ties the parameter to the tool ('for the supplied management token') but adds no meaning beyond that — no format, source, or validity constraints, which the schema only encodes as a regex pattern.

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 specific verb and resource: returns the last five retained revisions of a private draft, keyed by management token. The scope (five retained revisions) is concrete, though it never names a sibling tool or explains how it differs from get_gift or revise_custom_game. Note the tool name says 'gift_history' while the description talks about a 'draft', a mismatch an agent must resolve from the title.

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 'for the supplied management token' implies the prerequisite but gives no when-to-use condition, no when-not-to-use, and no alternative such as get_gift or revise_custom_game. The agent must infer that this tool is for auditing prior draft revisions.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior: a job has intermediate stages, and a completed job yields title, cast, play link and a management link that grants private sender access — a security-relevant disclosure. It omits error/not-found behavior and any rate limits.

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, front-loaded with the core behavior, then return contents, then the privilege caveat on management links. No filler and nothing restated from the title.

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?

With no output schema, the description carries the return-value burden and does so for the completed case, which is what an agent needs. The incomplete-job return shape and failure cases are unstated, a minor gap for a single-parameter status tool.

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?

There is one parameter with 0% schema description coverage, so the schema contributes only a type and regex pattern. The description says the key is a private idempotency key that identifies the job, which adds meaning, but it doesn't explain where the key comes from or how it relates to the creation 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?

States a specific verb and resource: returns the current stage of a game generation job, consumed by its private idempotency key. This is clearly distinguishable from creation siblings like make_game and revise_custom_game, which act on the game rather than reporting job status.

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 the usage pattern (poll a job previously submitted, using its idempotency key) but never states when to call it, how often to poll, or what to do instead. No alternatives or exclusions are named, so routing remains inferential.

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?

Goes well beyond the annotations: it discloses asynchronous behavior ('returns immediately with build progress'), a daily free allowance quota, an OAuth sign-in / handoff URL fallback path, and explicit safety guarantees ('never charges anyone or sends messages'). This is the kind of operational detail annotations cannot express.

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?

Four tightly packed sentences with the core action front-loaded and no filler. The quota/OAuth details are relevant but slightly interrupt the primary purpose statement; overall still efficient.

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?

With no output schema, the description does the work of explaining the return (immediate build-progress response, plus OAuth request or handoff URL on exhaustion). For a fire-and-forget async generator this is nearly sufficient, though it could say more about how progress is polled (e.g., via get_made_game).

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 all four parameters are already documented, including the 64-hex idempotency key and the brief contents. The description echoes the brief's role ('sender's supplied habits or inside jokes') but adds no format or constraint detail beyond the schema, so the baseline 3 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?

States a specific verb and resource: 'Starts generation of a small browser game about one person.' The scope (one recipient, derived from supplied habits/inside jokes) is concrete. However, it never distinguishes itself from siblings like create_custom_game, revise_custom_game, or get_made_game, so the agent must infer the boundary.

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?

Implicit usage context is present (quota-limited free generation, OAuth handoff when allowance is exhausted), but there is no explicit 'use this when X, use create_custom_game instead when Y' guidance despite four closely related sibling tools. The agent is left to infer the routing.

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 cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description goes further by disclosing optimistic-concurrency behavior: a stale expectedRevision is rejected to prevent clobbering another edit. That is exactly the kind of conflict/overwrite semantics an agent cannot infer from 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?

Three compact sentences, each earning its place: overwrite behavior, required credentials, and stale-revision guard. The most decision-relevant fact (replacement) is front-loaded.

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 non-idempotent mutation with 11 required/optional params, a nested game object, and no output schema, the description covers auth and concurrency well but leaves most field semantics and the post-revision state (does it return the new revision number?) unaddressed. Adequate but with clear gaps.

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 0% across 11 parameters, so the description must carry the meaning. It only explains managementToken and expectedRevision (and the expectedRevision rule); fields like theme, occasion, message, recipient, sender, and recipientEmail are left entirely to inference from their names.

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?

Specific verb ('Replaces') plus resource ('an existing private draft with supplied HTML and game details') immediately distinguishes this from the sibling create_custom_game. An agent can tell revise vs create 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?

It states the preconditions for use, namely that the draft's management token and current revision number are required, which tells the agent this only applies to an already-existing draft. It does not, however, explicitly contrast with create_custom_game or name the condition that selects one over the other.

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