diff

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

Annotations already declare readOnly, idempotent, and non-open-world, so the safety profile is covered. The description adds real context beyond that: the failure condition (errors if the repo is not enrolled) and a definition of what counts as drift.

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 dense sentences, front-loaded with the output definition and then the three invocation modes. No filler or redundant restatement of the tool name.

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 no output schema, the description compensates by describing the returned content (added/removed/body-hash-changed files and symbols) and the error case. It stops short of describing output shape or ordering, but is adequate for a 5-param 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 coverage is 100%, so baseline is 3, but the description goes further by explaining the pairwise relationship of a+b, the standalone meaning of since, the default fallback with no parameters, and the session pinning modifier. That interaction logic is not fully captured by the per-property schema text.

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 computation (structural drift) and enumerates the exact output domain: files and symbols added, removed, or whose body hash changed. An agent can tell this apart from hash/structure siblings, though the description does not explicitly name when those siblings are preferable.

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?

Spells out three distinct calling modes: a+b diffs two snapshots, since=label diffs a labeled snapshot vs live code, and the default diffs latest snapshot vs live code. This is genuine mode-selection guidance, but it does not address when to reach for this tool over a sibling.

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