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

With no annotations, the description carries the full burden. It discloses that a new editable draft is created in a sandbox, implying non-destructive behavior and isolation. However, it does not mention side effects like overwriting existing outputs, required permissions, or reversibility, leaving gaps.

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 with no fluff. It conveys the core action and destination efficiently, making it easy 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?

The description is too minimal for a build tool with no annotations or output schema. It omits return values, error conditions, and the relationship to sibling tools. An agent lacks enough context to know when to invoke it in a workflow or what to expect as a 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?

Schema coverage is 0%, so the description must compensate. It implies that manifest_path is the input manifest and output_root is the destination, adding meaning beyond bare parameter names. Yet it does not explain parameter formats, constraints, or how they interact, leaving some ambiguity.

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 action: compile a version-1 edit manifest into a new editable draft in a sandbox output root. It names the resource, the transformation, and the destination, which distinguishes it from siblings like validate, publish, or doctor.

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 provides no guidance on when to use this tool versus its siblings. It does not mention alternatives, prerequisites, or any conditions for selection. An agent would have to infer usage from the verb 'build' without explicit direction.

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 provided, the description carries the full burden of behavioral disclosure. It only says 'Check', which implies a non-mutating operation, but it does not explicitly state that it is read-only, describe side effects, return value, or required permissions. Critical gaps for a diagnostic tool.

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 concise sentence, front-loaded with the verb 'Check', and contains zero filler. Every word contributes to listing the checked items, though those items could be clearer.

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?

There is no output schema, so the description should explain what the tool returns or what 'checking' produces (e.g., a report, success/failure). The phrase 'create-new safety boundary' is obscure and not explained. For a diagnostic tool, the absence of result/return information is a major gap.

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 the undocumented parameter. It mentions 'draft-root' as one of the check items, linking it to the drafts_root parameter, but does not explain expected values, the meaning of null/default, or how the parameter affects the check. The optional nature is left 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?

The description uses a specific verb ('Check') and names distinct resources (JianYing Pro, draft-root, FFmpeg, create-new safety boundary), which separates it from the sibling build/validate/publish tools by implying a diagnostic role. However, it does not specify what kind of checks are performed (e.g., version, availability, config), leaving some ambiguity.

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 guidance on when to use this tool versus the sibling tools. The name 'doctor' hints at troubleshooting, but the description provides no usage scenarios, prerequisites, or exclusions. No mention of when to prefer this over validate or build.

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. It discloses two important behaviors: it refuses overwrite and requires JianYing closed. However, it doesn't mention what happens on failure (e.g., error if JianYing is open), whether it modifies the draft, or any side effects beyond copying. The disclosed behaviors are useful but not comprehensive.

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 short sentences with no filler. The key constraints ('Refuses overwrite', 'requires JianYing closed') are front-loaded and 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?

For a tool with 2 params, no output schema, and no annotations, the description covers the core purpose and two critical constraints. However, it lacks details on parameter semantics (especially 'drafts_root'), error behavior, and what 'validated' means in practice. It's adequate but not complete.

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. It doesn't explain the parameters at all: 'project_path' and 'drafts_root' are only defined by their names and types. The description's mention of 'draft' and 'library' gives some context, but it doesn't clarify what 'drafts_root' means or how it relates to 'project_path'. This is a gap, but the parameter names are fairly 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?

The description states a specific verb ('Copy'), a resource ('validated NEW draft'), and a destination ('JianYing's library'), which clearly distinguishes it from siblings like jianying_validate_project and jianying_build_project. It also adds a key constraint ('Refuses overwrite'), making the purpose more precise. However, it doesn't explicitly name the sibling it differs from, so it's not 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 description implies when to use this tool: after validation ('validated NEW draft') and before publishing, and it gives a clear exclusion ('Refuses overwrite'). It also states a prerequisite ('requires JianYing closed'). It doesn't explicitly name alternatives like jianying_build_project, but the context is clear enough for an agent to select 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 must disclose behavior itself, but it only states that validation occurs. It does not say whether the tool is read-only, whether it modifies files, what happens on invalid references, or what success/failure looks like. This is a significant gap for a validation tool with no output 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?

The description is very concise and front-loaded, with no wasted words. However, it may be overly terse, omitting important behavioral and usage context that an agent would need to invoke the tool correctly.

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 validation tool with one undocumented parameter, no annotations, and no output schema, this description is incomplete. It lacks return value expectations, failure semantics, and when-to-use guidance. An agent cannot tell what a successful validation looks like or how to 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?

Schema description coverage is 0%, and the description does not explain what project_path should point to, what format it must be in, or how it relates to the draft/timeline/materials. The phrase 'local file references' hints that a local project file is targeted, but that is not enough to compensate for the missing schema documentation.

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 uses a specific verb ('Validate') and names concrete resources ('draft identity, timeline, materials, and local file references'), which distinguishes it from build/publish/doctor siblings. However, 'draft identity' is somewhat ambiguous, so it does not fully reach the 5-level of precision.

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 use this tool versus jianying_doctor, jianying_build_project, or jianying_publish_project. No prerequisites, ordering, or exclusions are mentioned; an agent must infer that validation fits before build/publish.

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