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

With no annotations at all, the description carries the full behavioral burden yet discloses very little. It doesn't say whether the conversion is lossy (the lossy_fixes param suggests it is), how font embedding behaves, what happens if the HTML violates the contract, or whether output_path is overwritten.

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 tight sentence with the action and the output destination front-loaded. Nothing is wasted, though there is also very little substance.

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 covers return values, but for an unannotated file-writing tool with 6 undocumented parameters, the description is far too thin. Critical context about the HTML contract, lossy conversion, and font handling 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% across 6 parameters, and the description only names output_path. The non-obvious parameters — lossy_fixes ('apply'), font_strategy ('auto'), embed_fonts, base_dir — receive no explanation anywhere, leaving the agent unable to choose values 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?

States a specific verb and resource pair: compile restricted HTML into a native editable .pptx and write it to output_path. The word 'restricted' hints at a contract, but the description never distinguishes this from validate_html or get_contract, which are the obvious siblings in the pipeline.

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 guidance and no mention of the validate_html / get_contract siblings that clearly gate this conversion. An agent must infer that HTML should be validated first and that 'restricted' refers to a contract.

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 never states that this is a read/export operation with no side effects, says nothing about permissions, size of output, or what the two formats contain beyond a one-word contrast (精简规范 vs 完整契约).

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 tight sentence with the resource front-loaded and the two format options immediately after. Efficient, though it is perhaps too terse for an unannotated 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 return-value detail need not be in the description, and the format semantics are covered. But with no annotations for a 1-param export tool, the description leaves gaps about what the contract contains and whether the call has any side effects.

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% and the format property has no enum or description, so the definition is the only place that explains format=llm (condensed spec) vs format=json (full contract). That is meaningful added value beyond the schema, though it omits the default value and any constraints.

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 object (导出契约 / export the contract) and explains the two formats, but never says what 'contract' actually is — schema contract, tool contract, or something else — so the purpose remains fuzzy. The sibling tools (validate_html, convert_html, ppt_*) offer no contrast to orient the agent.

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 pick format=llm (condensed spec) vs format=json (full contract), which is useful implied usage guidance. However, it does not state conditions, exclusions, or alternatives explicitly, and the default (llm) is only visible in the schema.

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. "盘点" and the extractive outputs (palette, fonts, shape inventory) strongly imply a read-only analysis, but the description never explicitly states that it is non-mutating, requires a valid local file, or has any side effects. It does at least disclose what the tool produces.

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 compact sentence, front-loaded with the core action "盘点参考 pptx" and then the extracted artifacts. The parenthetical examples and the trailing reversal rationale are dense but each clause adds information; no filler sentences.

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 structure need not be explained. However, for a tool with no annotations and 0% schema description coverage, the description should clarify that it is read-only and what the pptx_path must be. It covers the analysis outputs well but leaves these operational 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%, so the schema only provides the name "pptx_path" with no description. The description adds a little meaning by framing it as a "参考 pptx" (reference deck), but it does not explain path format, extension requirements, or whether the file must be local. For a single self-evidently named parameter, this is minimally acceptable.

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+resource: inventorying a reference pptx, and enumerates what the outline covers (theme palette/fonts, per-page shape list, preliminary role identification). It also links the output to slide selection for the reversal workflow, which helps distinguish it from siblings like ppt_reverse, though it doesn't explicitly name the sibling.

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?

"选择性逆转的选片依据" implies this tool is used upstream of the reversal step to choose slides, giving some usage context. However, there is no explicit when-to-use/when-not guidance, no prerequisites (e.g., file must exist locally), and no explicit routing away from siblings such as ppt_reverse or convert_html.

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 does disclose important behavior: output is written to disk, and fragments no larger than 12KB are returned inline. It does not discuss overwrite behavior, permissions, or whether out_dir contents may be replaced, which matters for a file-writing 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 compact and front-loaded, covering the core operation, selection behavior, and output handling in two sentences. The term "契约子集" is somewhat opaque, but there is no wasted text.

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 core operation and output behavior are adequately described, and an output schema exists for return values. Still, for a six-parameter tool with no annotations and 0% schema coverage, the missing explanations for include_html and placeholder_text leave meaningful 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%, so the description must compensate. It clarifies pages/elements selection semantics, but leaves include_html (default "auto") and placeholder_text entirely unexplained, and does not add detail for pptx_path or out_dir beyond 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?

The description gives a specific verb and resource: reverse a reference pptx into restricted HTML (a contract subset) for reuse. It implicitly distinguishes from siblings like ppt_outline and validate_html, though it does not 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?

It explains that omitting pages/elements performs a full reversal while supplying one enables selective reversal, which is useful usage context. However, it gives no guidance on when to use this tool versus convert_html, validate_html, or get_contract.

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 exist, so the description carries the full burden. It discloses the report shape (errors/warnings/fixes) but says nothing about whether validation mutates the input — notably the 'lossy_fixes' parameter defaults to 'apply', implying changes may be applied, which the description never explains.

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 purpose and return shape come first. Slightly terse given how much behavior (fixes, font strategy) is left unexplained.

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 output schema covers return values, but with no annotations and 0% parameter description coverage, the description leaves the mutation semantics of lossy_fixes and the meaning of font_strategy unaddressed. For a 3-param validation tool with side-effect ambiguity, this is insufficient.

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, but it only hints that the html input is 'restricted'. The lossy_fixes and font_strategy parameters — including their defaults and enum-free allowed values — are completely unaddressed in both schema and description.

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+resource: validating restricted HTML against a contract, plus what the report contains (errors/warnings/fixes). It is clear what the tool does, but it never names or contrasts itself with the sibling convert_html, so differentiation is left to inference.

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 validate versus when to use convert_html, get_contract, or the ppt tools, and no stated preconditions. The agent must infer usage from the description alone.

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