diff

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

With no annotations, the description carries the full burden and does well: it discloses the output shape (structured symbol records, iterable directly) and the change taxonomy, which goes beyond the schema. It does not discuss ordering, whether results are paged/truncated relative to `limit`, or read-only guarantees, which are minor omissions for a diff tool.

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 sentences, both front-loaded: the first defines the operation and its output, the second routes the agent away from `git diff`. No filler or restated boilerplate.

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, so the description correctly steps in to describe the return value as symbol records grouped by change type. It is sufficient to call the tool correctly; only minor gaps remain (ordering, how `limit` truncation is signaled).

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 100% and every parameter (base, limit, exclude/include precedence, project_root, exclude_tests) is fully documented in the schema itself. The description adds no parameter-level detail beyond the schema, so the baseline 3 applies.

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 ('symbol-level diff between a git revision and the working tree') plus the exact output categories (added/removed/moved/body-changed symbols). It distinguishes itself from the closest non-MCP alternative, `git diff`, and from line-hunk tools generally.

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?

Explicitly names the alternative ('git diff' + manual scanning) and the scenario that selects this tool ('PR review'), and explains why: structured symbol records vs. unified-diff text. Nothing is left to inference about when to reach for it.

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