get_tracked_changes

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

With no annotations, the description carries the full burden and explicitly declares 'Read-only,' which is the key safety-relevant behavior. It also discloses the scope ('Every tracked change') and the kind of data returned. It could add details like ordering or pagination, but for a read-only retrieval tool the core transparency is well 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?

Three dense sentences, no filler. The first sentence states the resource and returned fields, the second covers filtering, and the third gives routing and safety. Information is front-loaded and every sentence earns 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?

The presence of an output schema reduces the need to describe return values. The description covers the main behavior, filtering, alternative tools, and read-only safety. It is slightly incomplete in not explicitly stating what document 'file_path' refers to, though this is fairly inferable from the tool name and context.

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 must compensate. It adds real meaning for the 'author' parameter ('Filter by author to see one reviewer's edits'), helping map it to a use case. However, it does not explicitly describe 'file_path,' leaving that important required parameter to inference from its name and context.

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 what the tool returns: every tracked change with type, author, date, affected text, and paragraph location. It implicitly names the operation (list/retrieve) and distinguishes itself from revision_summary/revision_analytics by pointing out those are aggregate views, and from accept_revisions/reject_revisions by noting those resolve changes.

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?

Provides explicit routing guidance: 'Filter by author to see one reviewer's edits' gives a concrete use case, and 'Use accept_revisions/reject_revisions to resolve, or revision_summary/revision_analytics for aggregate views' states when alternatives should be chosen. The tool's own niche is clear by exclusion.

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