Diff two committed versions

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

Annotations already mark readOnlyHint=true, so the description adds value beyond that by explaining the default ref behavior (ref_b=HEAD, ref_a=previous commit) and the requirement for PORTAL_VC_DIR. It also notes that the file list is always complete even when max_chars caps the diff text. No contradictions with annotations.

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?

The description is three sentences, front-loaded with the core purpose, then defaults, then a usage warning and environment requirement. Every sentence earns its place with no redundancy.

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?

Given the output schema exists and annotations are present, the description covers the key behavioral aspects: two scoping modes, default refs, the pre-restore use case, and the PORTAL_VC_DIR dependency. It doesn't enumerate potential errors or return structure, but the output schema handles that, and the description is otherwise 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 100%, so the baseline is 3. The description adds meaning by explaining how ref_a/ref_b defaults are calculated, that passing hashes from vc_log enables arbitrary pairs, and that max_chars caps diff text while the file list remains complete. This enriches the parameter understanding beyond the schema.

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 clearly states the tool produces a unified diff between two committed versions, and distinguishes between scoping to a single record or the whole repo. It is differentiated from sibling tools like vc_status (status) and vc_log (log) by focusing on diffing commits.

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?

The description gives clear context for when to use this tool, specifically advising to inspect the diff BEFORE restore_resource. It also mentions passing hashes from vc_log, implying vc_log is the source for refs. It lacks explicit exclusions or a named alternative for 'when not to use', but the usage guidance is solid.

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