Read local source or guide

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: 'Use nextOffset to continue without omission' discloses pagination behavior, and 'Offset is a JavaScript UTF-16 string index' discloses a subtle technical detail that could trip up agents. It doesn't describe error cases, but the annotations carry the safety burden.

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?

Three sentences, zero filler. The core action and scope are front-loaded, the pagination contract is stated, and the technical offset detail is included. Every sentence 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 simple read tool with strong annotations (readOnly, idempotent, non-destructive), the description covers the essential behavioral contract: bounded ranges, pagination via nextOffset, no network/filesystem access, and the UTF-16 offset semantics. It doesn't mention what happens on invalid paths or whether the output schema includes nextOffset, but the pagination hint implies it. Given the tool's simplicity, this is nearly 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 does: it explains the meaning of offset ('JavaScript UTF-16 string index') and the pagination contract ('Use nextOffset to continue without omission'). It doesn't explicitly explain maxChars, but the name is self-explanatory and the schema bounds it. The description adds real meaning beyond the raw schema.

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 ('Read'), a specific resource ('exact bundled file content'), and a precise scope ('bounded character ranges'). It also distinguishes itself from siblings by explicitly noting 'no network or user filesystem access', which separates it from search_local_references and get_reference_outline.

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 clearly implies when to use this tool: when you need exact bundled file content in bounded ranges, and explicitly says what it does NOT do ('no network or user filesystem access'). It doesn't name alternative siblings explicitly, but the exclusion of network/filesystem access plus the 'bundled file' scope gives clear context. It could be improved by naming search_local_references as the alternative for searching, but the guidance is still strong.

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