Read a bounded byte range from a file on disk at a zero-based offset, without touching editor buffers, for precise binary inspection.
Read bounded bytes from disk by zero-based byte offset; never read an editor buffer.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| length | Yes | ||
| offset | Yes | ||
| text_preview | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavior beyond that: reads are bounded, disk-sourced, and byte-offset addressed rather than buffer/line-based. It stops short of disclosing what happens on out-of-range offsets, any max length limit, or how the text_preview flag alters output.
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 a semicolon-delimited exclusion clause; no filler, no restatement of the tool name. Every clause carries information the caller needs.
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?
No output schema exists, but for a read-only byte fetch the description needn't explain return format. The real gap is invocation correctness: text_preview is undocumented anywhere, so an agent cannot know whether it gets raw bytes or a decoded preview, and length/offset edge behavior is unstated.
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 carry parameter meaning. It clarifies that offset is zero-based and that length bounds the read, and 'from disk' implies path semantics, but the fourth parameter (text_preview, default true) is completely unexplained in both schema and description, and length limits/path format are left unspecified.
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 ('Read bounded bytes from disk') with a precise addressing mode ('zero-based byte offset'), and explicitly contrasts scope with a sibling capability ('never read an editor buffer'). An agent can tell this apart from editor_read without opening either schema.
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 clause 'never read an editor buffer' functions as a when-not rule, steering the agent to the editor_* tools for buffer content. However, it never names the alternative tool or explains when to prefer binary_read over binary_search or binary_inspect, so the routing is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.