Read characters from a specific row and column on the mainframe screen to inspect or verify displayed data.
Return text at a specific screen position.
Args: row: 1-based row index (1-24). col: 1-based column index (1-80). length: Number of characters to read.
| Name | Required | Description | Default |
|---|---|---|---|
| col | Yes | ||
| row | Yes | ||
| length | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. 'Return' implies a read-only operation, and the coordinate ranges (1-24, 1-80) give some screen size context. However, it doesn't disclose what happens on out-of-range inputs, whether it returns an empty string for blank areas, or explicitly state that it has no 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?
The description is compact and well-structured: a single clear purpose sentence followed by a bullet-like Args block. Each parameter line adds specific meaning without redundancy or fluff, and the key purpose is front-loaded.
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 tool has an output schema, return type details are covered elsewhere. The description supplies enough for correct invocation: coordinate ranges, character count, and the default of 80. It doesn't address when to choose this over siblings, but that gap is more about usage guidelines than operational completeness.
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?
With schema description coverage at 0%, the description provides essential semantics: row and col are 1-based with valid ranges, and length is the number of characters to read. This fully compensates for the barren schema. The default length of 80 is only in the schema, but the description still clarifies each parameter's purpose.
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 opening sentence 'Return text at a specific screen position' clearly states a specific verb and resource, making the core function obvious. It differentiates from siblings like get_screen or find_text by emphasizing location-based reading, though it doesn't explicitly name an alternative.
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 indication of when to use this tool versus alternatives such as get_screen, find_text, or analyze_screen_fields. There is no mention of context, prerequisites, or exclusions, leaving the agent to infer appropriate usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.