Read patch by file or chunk

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), so the description adds value with the 50000-unit read cap, the 'follow nextOffset until hasMore is false' loop, and the requirement to bind each read to the full preview hash. The hash-binding constraint is a meaningful behavioral detail beyond annotations, though failure behavior on mismatch is left implicit.

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?

Four short, front-loaded sentences with no filler; the core read action leads, followed by path selection, hash binding, pagination, and the alternative. Every sentence adds distinct operational value.

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?

With an output schema present, return values need not be described, and the description covers pagination, size cap, hash binding, and sibling routing. The only notable omission is the meaning of taskId, but otherwise it is complete for a read 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%, so the description carries the burden and largely succeeds: it explains limit (max 50000 UTF-16 units), path (optional changed path), offset (via nextOffset), and expectedSha256 ('bind every read to the full preview hash'). Only taskId is left unexplained, keeping it short of a full 5.

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 ('Read ... the current patch') and clarifies scope (up to 50000 UTF-16 units, optional path selection). It also distinguishes itself from the sibling antigravity_preview by routing metadata lookups there, so an agent can tell the two apart without opening a 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?

Gives clear operating context: select a 'changed path' optionally, 'Follow nextOffset until hasMore is false' for pagination, and use 'preview with includePatch false for metadata' as the alternative. It names an alternative tool but stops short of explicit when-not-to-use conditions.

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