单元格显示文本(深度提取)

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

The description discloses the internal behavioral logic beyond the readOnlyHint annotation: it specifies the priority order of text sources (scenegraph first, then fallbacks) and states that it annotates the source of the hit. This is detailed and transparent, covering what the agent needs to understand about the tool's operation without contradicting the annotation.

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 dense, single paragraph that front-loads the core function ('深度提取单元格的显示文本'), then efficiently explains the fallback chain and the usage note. Every sentence adds substantive value with no repetition or fluff, making it well-structured and concise.

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 thoroughly covers the extraction logic and the key usage scenario. Since an output schema exists, the return structure is not expected to be repeated. However, the lack of parameter guidance is a notable gap, especially given zero schema coverage. Minor edge cases (e.g., all fallbacks failing) are not addressed, but overall the description is complete for a read-only 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?

Schema description coverage is 0%, and the description provides no additional meaning for the four parameters (col, row, tab_id, table_index). It does not clarify indexing conventions (0- vs 1-based), when optional parameters are required, or any formatting details. The parameter names are somewhat self-explanatory, but the description fails to compensate for the lack of 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 clearly states the tool's core function: deep extraction of a cell's display text. It specifies the resource (cell in a vtable) and the action (extract display text), and details the fallback priority chain (scenegraph rendered text, overflow full text, display value, raw value, business record field). It also explicitly positions this tool as the authoritative source when getCellValue disagrees with the page, distinguishing it from simpler cell read tools.

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 a clear usage condition: 'When getCellValue and page display are inconsistent, use this as the authority.' This tells the agent when to prefer this tool. However, it does not name specific sibling alternatives or explicitly state when not to use it, leaving some inference to the agent.

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