Preview isolated changes

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

Annotations already declare this a safe, closed-world, non-destructive read, so the safety profile is covered. The description adds the finished-task precondition and indicates the payload includes 'client-reported test evidence with stale markers', which hints at freshness semantics. It does not describe error behaviour, size limits, or what happens when includePatch is omitted.

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?

Two tight sentences, front-loaded with the payload contents and ending on the precondition. It is compact, but the enumerated return fields largely restate what the output schema already provides, so much of the sentence does not earn 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?

An output schema exists, so return values need not be enumerated, leaving the description thin on the things that matter: neither input parameter is explained and no sibling differentiation is offered. For a read tool with two undocumented parameters and many similar siblings, it is under-specified.

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 full burden for taskId and includePatch, yet it explains neither. The mention of 'patch' refers to an output field, not the includePatch input, so it may even muddy which parameter controls patch inclusion.

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 outlines a diff/preview payload (A/M/D files, stats, patch, SHA-256, test evidence), which conveys what the tool returns and, indirectly, what it does. However it frames the tool as a return-value list rather than a verb+resource, and it names no sibling such as antigravity_read_patch or antigravity_read_result, so the agent cannot distinguish it from those on the description alone.

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?

"Requires a finished task" is a genuine state precondition that tells the agent when the call will be valid, which is real usage guidance. There is no routing against alternatives (read_patch, read_result, result) and no statement of when NOT to use it, so usage is only partially covered.

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