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

Annotations already flag destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the bar is lower, yet the description adds real context: it replaces ALL current questions, and it performs an unauthenticated request to verify the public version. The destructive scope is disclosed in prose, which is valuable beyond the boolean hint.

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 compact sentences, front-loaded with the operation sequence and then the intended scenario. Nothing is wasted, although the second sentence's quotation of a user phrase is slightly loose.

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. For a destructive multi-step tool the description adequately covers the operation sequence and the replace-all scope, leaving only minor gaps around per-step failure behavior.

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 75%, so the schema already documents form_url, anonymous, and response_format, including the anonymous-vs-login nuance. The description only echoes '保存匿名设置' and adds no format, syntax, or constraint detail beyond the schema, making the 3 baseline 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 states a specific composite verb set (replace questions, save anonymous setting, publish, verify public version) against a concrete resource (Tencent Docs collection form). It distinguishes itself as the 'complete workflow' variant, implying it differs from the narrower siblings, though it never names them explicitly.

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?

'适用于"建好后直接给我可预览链接"的完整流程' clearly states the usage context that selects this tool over the step-by-step siblings. It stops short of explicit exclusions, e.g. telling the agent to use replace_form_questions or publish_form when only one step is wanted.

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, and the closing clause '不修改任何内容' largely restates that. The description adds the functional scope of the read, but omits openWorldHint implications (external link fetching), auth/permission requirements, and rate-limit behavior, so it adds only modest value beyond 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?

A single compact sentence with the read scope front-loaded and no filler. The trailing '不修改任何内容' clause is close to redundant with the readOnlyHint annotation, which slightly dilutes the value of the space it occupies.

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 an output schema present, return values need not be explained, and the description covers the fields surfaced plus the no-modification guarantee. It falls short only on use context (when to inspect rather than publish) and external-fetch/auth caveats implied by openWorldHint.

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%; both form_url (public link) and the response_format enum are fully documented in the schema, and the description adds no syntax, format, or linking detail beyond it. Baseline 3 is correct when the schema does the heavy lifting.

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?

Names a specific verb (读取) and resource (收集表) and enumerates exactly what is returned: 标题、发布状态、题型、当前账号权限. An agent can distinguish this read-only inspector from the mutating siblings (publish/build/replace) without opening a schema, though no sibling is named explicitly.

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 explicit when-to-use guidance, no named alternative, and no prerequisites or ordering advice (e.g. 'use before publish_form'). Usage is only faintly implied by the statement that nothing is modified.

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 declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=true, already covering the safety and idempotency profile. The description adds the useful detail that it verifies the public version via a cookie-less read-back, which enriches the behavior beyond the annotations, but does not cover other behavioral aspects like preconditions or side effects.

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 front-loads the primary action (立即发布当前草稿) followed by the verification step. It is appropriately sized and wastes little, though it could be marginally clearer on the publishing target.

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 simple two-parameter schema, one of which is required, and annotations covering the safety profile, the description is sufficient for an agent to invoke the tool. No output schema is provided, but the description notes the read-back behavior, which partly compensates. Minor gaps remain in usage conditions relative to siblings.

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%; both form_url and response_format are fully described in the schema. The description adds no parameter-specific detail beyond what the schema provides, so a 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?

States a specific verb (发布/publish) and resource (当前草稿/the current draft form), and adds a behavior: re-reading the public version without auth cookies. The distinction from sibling tencent_docs_build_and_publish_form is implied (this publishes an existing draft) but not explicit, 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 '当前草稿' (current draft) implies the tool applies to an already-created draft, which is circumstantial usage guidance. However, there is no explicit when-to-use vs. when-to-use-the-siblings guidance (e.g., vs. tencent_docs_build_and_publish_form), so it remains implied rather than 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?

Adds context beyond the annotations (destructiveHint=true already covers the replace semantics): the creator/admin authorization requirement and the post-call read-back that verifies title, question order, and question type. This read-back/verification behavior is a meaningful trait not captured by any structured field.

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: the action and its non-publishing limit are front-loaded, followed by the permission constraint and the verification behavior. 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?

Authorization, non-publication, and read-back verification are covered, and an output schema exists so return values need not be described. The main residual gap is what happens to data on the existing form (full overwrite vs merge), which is relevant for a destructive replace.

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 67% and the nested $defs (FormSpec, QuestionSpec, enum types) are well documented inline. The description adds no parameter-level detail, so the baseline of 3 for schema-doing-the-work 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?

States a specific verb and resource: '完整替换一份已存在的腾讯文档收集表题目' (completely replace the questions of an existing form). The clause '但不发布' (but does not publish) cleanly distinguishes it from the publish_form and build_and_publish_form siblings without opening their schemas.

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?

Establishes usage context ('已存在' = must already exist) and a hard precondition ('只允许创建者或管理员执行'). The '但不发布' note implicitly routes the caller elsewhere to publish, but no sibling is named explicitly as an alternative for that next step, so it stops short of full when/when-not guidance.

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