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

No annotations are provided, so the description carries the full burden. It does disclose meaningful traits — the draft is persistent and versioned, and no Google Form is created — which implies a safe, reversible, local-only operation. However, it omits auth requirements, whether each call creates a new version or overwrites, and any limits on draft count.

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 with no filler; the differentiating clause is placed immediately after the core action. Nothing to trim.

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?

An output schema exists, so return values need not be explained, and the schema documents the spec shape. Still, with no annotations the description should say more about versioning semantics and side effects — key facts for a tool whose siblings include patch, undo, and publish.

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 required parameter (spec) with 0% description coverage, and the description never mentions it or explains that it is a complete form definition. The schema's internal $defs are self-describing (field descriptions, enums, bounds), which does much of the work, but the prose adds nothing about the 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 (save) and a specific resource (persistent, versioned form draft), and the clause 'without creating a Google Form' implicitly separates it from publish_form_draft and update_existing_google_form. It never names a sibling explicitly, so it falls short of a 5.

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 'without creating a Google Form' hints at the use case (drafting before publishing), but there is no explicit when-to-use/when-not guidance and no reference to publish_form_draft, patch_form_draft, or undo_draft_change as alternatives. Usage is inferable but not stated.

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?

No annotations are provided, so the description carries the full behavioral burden. 'Persistent' hints the draft survives beyond a session, but nothing is said about auth requirements, behavior when the draft_id does not exist, or whether unpublished changes are included in 'current version'.

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 with no filler. It is efficient, though its brevity is the same trait that leaves the usage and parameter gaps unfilled.

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?

The tool is simple (one required param) and an output schema exists, so return values need not be explained. Still, with no annotations and an undocumented parameter, the description should say more about identity/format of draft_id and failure behavior when a draft 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 0% for the single required parameter, so draft_id is completely undocumented in structured data. The description never mentions the parameter, its expected format, or where to obtain a valid ID, leaving the gap unaddressed.

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 ('Return') plus resource ('form draft') and a scope qualifier ('current version'), which signals a read of the latest state rather than a mutation. It implicitly contrasts with mutating siblings like patch_form_draft or publish_form_draft, but never names them, so differentiation is inferred rather than stated.

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 no when-to-use guidance and no alternatives. An agent must guess whether to call this versus preview_google_form or patch_form_draft, and 'current version' hints at a read-before-edit pattern without ever saying so.

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?

With no annotations, the description carries the full burden. 'Report' implies a read-only, side-effect-free check, which is useful behavioral context, but it does not explicitly state that the operation is safe, idempotent, or that it requires no authorization itself.

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 communicates the entire purpose without filler. Every word earns its place for such a simple tool.

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?

An output schema exists, so the description need not explain return values. The tool is low-complexity and the description adequately covers its purpose, though it could mention prerequisites or when to invoke it relative to the sibling form tools.

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 per the scoring rules the baseline is 4. The description correctly does not attempt to describe nonexistent parameters, and the empty schema is self-explanatory.

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 ('Report') and a precise resource ('whether the active user's Google authorization is configured'). This clearly distinguishes it from all sibling tools, which operate on form drafts rather than authorization state.

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 purpose implies the usage context (checking whether authorization is ready before attempting form operations), but the description offers no explicit when-to-use guidance or prerequisites. It does not mention alternatives or when not to call 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?

With no annotations, the description carries the full burden, yet it does disclose one meaningful behavioral trait: unrelated content is preserved, implying a partial/non-destructive merge rather than a full replace. It omits atomicity (do all operations apply or does one failure roll back?), reversibility, auth requirements, and whether the draft must exist first.

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 with no filler. It is efficient, though arguably under-sized for an operation that supports ten distinct mutation kinds.

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 high-complexity tool with a large discriminated-union input, no annotations, and no parameter documentation, one sentence is far too thin. An output schema exists so return values needn't be described, but atomicity, auth, operation coverage, and error behavior are all 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 0%, so the description must compensate for both draft_id and the operations array. It explains neither the draft identifier nor the discriminated union of ten operation types, leaving all meaning to be recovered from the raw schema.

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: applying targeted operations to a draft. It's clear this is an in-place edit tool, and 'preserving unrelated content' hints at its patch semantics. However, it doesn't differentiate itself from siblings like update_existing_google_form or create_form_draft, nor hint at the operation types available.

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 guidance on when to use this versus publishing, creating, updating, previewing, or undoing. Siblings like publish_form_draft and undo_draft_change strongly imply ordering/alternatives the description never addresses. The agent must infer the whole 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?

With no annotations, the description carries full behavioral burden. It does disclose the key trait that nothing is created or persisted, but it does not say what validation actually covers, what happens on an invalid spec, or whether failures raise errors or return a report — all material for a tool whose whole value is validation.

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 with zero filler; the no-side-effect qualifier is placed where it matters. It is arguably undersized for the complexity of the input, but every word earns its place.

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?

An output schema exists, so return values needn't be explained, but the tool's complex nested input contract and the substance of 'validate' are both unaddressed. For a validation/preview tool with a rich spec parameter, this leaves the agent guessing what is checked and what a failure looks like.

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% at the property level, and the description says nothing about the single 'spec' parameter. The nested FormSpec/SectionSpec/QuestionSpec structure (required fields, 75-section and 200-question caps, question types) is left entirely to the schema, so the description adds no semantic value for a complex, non-trivial input.

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 compound verb ('validate and preview') against a named resource ('a Google Form') and adds the crucial scope qualifier 'without creating or saving anything', which separates it from create_form_draft and publish_form_draft. It never names those siblings explicitly, so the differentiation is inferred rather than stated.

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?

'Without creating or saving anything' implies a pre-flight check to run before create/publish, which is useful implicit routing. However, no sibling is named and there is no explicit statement of when to prefer this over create_form_draft or get_form_draft.

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?

With no annotations, the description carries the full behavioral burden, yet it discloses nothing beyond the bare action. It does not explain the 'confirm' flag (default false, likely a dry-run gate), what 'expected_version' guards against, whether publishing is irreversible, what happens to the draft afterwards, or what auth is required.

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 with no filler or redundancy. It is efficient, though its brevity comes at the cost of the behavioral and parameter detail an agent needs.

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?

An output schema exists so return values need not be described, but for an unannotated mutation tool with 0% parameter documentation and a default-false confirm flag, the definition is too thin. It omits concurrency semantics, irreversibility, and preconditions that an agent must know before invoking it.

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% for three parameters, so the schema offers only titles like 'Confirm' and 'Expected Version' with no meaning. The description compensates only faintly: 'exact approved draft version' gestures at version pinning but never mentions draft_id, expected_version, or confirm, leaving two parameters entirely unexplained.

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 concrete verb and resource ('Create a native Google Form') and scopes it to 'the exact approved draft version', which distinguishes it from create_form_draft and preview_google_form. It never names a sibling explicitly, but the publish-vs-draft distinction is inferable from the phrasing.

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 explicit when-to-use or when-not-to-use guidance, and no mention of prerequisites such as the draft needing approval before publishing or how this relates to preview_google_form. The only usage signal is the implied precondition embedded in 'approved draft version', which is thin for a mutating publish operation.

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?

No annotations are provided, so the description carries the full burden. It does disclose a meaningful behavioral boundary — the change is confined to the draft and does not propagate to the live Google Form — but omits what happens at the earliest version, whether the rollback is itself reversible, and any auth requirements.

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 compact sentence that front-loads the action. Nothing is wasted, though "without touching Google Forms" is vague enough to be marginally less useful than a concrete statement like "does not modify the published form."

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?

An output schema exists so return values need not be explained, but with zero annotation coverage and 0% parameter documentation the definition leaves an agent guessing about identifier format and edge-case behavior. For a state-mutating rollback tool this is thin.

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% for the single draft_id parameter, and the description never addresses it beyond the indefinite article "a draft." An agent gets no format, source, or identifier guidance to compensate for the schema gap.

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?

"Move a draft back by one version" gives a specific verb and resource with a clear unit of change, and "without touching Google Forms" scopes it away from the publish/update siblings. It stops short of naming a distinct alternative tool, but the intent is unambiguous.

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 statement of when to use this versus get_form_draft, patch_form_draft, or publish_form_draft. The only implied guidance is the negative scope ("without touching Google Forms"), which hints it is a local-only rollback but never says so explicitly.

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?

No annotations are provided, so the description carries the full burden. It omits that the operation set includes destructive actions (delete_question, remove_option), that confirm/plan_token gate whether changes actually apply, and any auth or side-effect details. For a mutating tool with no annotation coverage this is a substantial gap.

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 with no filler. It is efficient, though the brevity shades into under-specification rather than tight communication.

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?

The schema is complex (10 discriminated operation variants, nested QuestionSpec) and no annotations exist, yet the description covers none of the preview/apply mechanics, destructive operations, or parameter roles. An output schema exists, so return values are not owed, but the operational model still is.

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% and the description explains none of the four parameters. The words 'signed' and 'plan' vaguely gesture at plan_token, but confirm, operations, and form_id are never addressed, leaving the most consequential controls (confirm, plan_token) undocumented.

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 (update) and resource (existing Google Form), and the 'preview or apply' phrasing hints at a two-phase workflow. However, 'signed targeted update plan' is left undefined, so an agent can't tell precisely what a plan is or how this differs from patch_form_draft 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?

No guidance on when to use this tool versus patch_form_draft, preview_google_form, or undo_draft_change. The 'preview or apply' wording implies a two-step flow but never states which parameter selects each mode, so the agent must infer it from the schema.

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