get_source_diff

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

The readOnlyHint annotation already establishes safety, and the description adds real value by disclosing what the response contains (status, unstaged, and staged changes) — important since there is no output schema. It does not mention size limits or behavior when a file has no changes, but the core behavioral picture is covered.

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?

One sentence with no filler, front-loaded with the verb and the scope, and every clause contributes — the staged/unstaged distinction and the explicit-selection constraint both matter.

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 correctly takes on the job of stating what is returned, and with only one parameter the burden is light. Missing path conventions and the empty-diff case keep it short of 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 coverage is 0%, so the description carries the burden; it does tell the agent that files must be explicitly selected, but gives no guidance on path form (repo-relative vs absolute) or the 80-item cap, leaving the single parameter partially specified.

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?

Names a specific verb (Read) and a specific resource (Git status plus unstaged and staged changes) scoped to explicitly selected source files, which clearly separates it from read_source_file and list_source_files. No sibling is named, so the differentiation is implicit rather than explicit.

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?

Usage is only implied: the reader infers this is for inspecting pending changes in files the caller already knows about, versus list_source_files for discovery or read_source_file for content. There is no statement of when not to use it and no named alternative.

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