revision_diff

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

With no annotations, the description carries the full burden. It discloses the output format (plain-text unified diff), that each side is labelled with timestamp, editor, and edit summary, and the limit clamping behavior. It does not explicitly state it is read-only, but that is implied by 'compare'. It does not mention error cases or rate limits, but the core behavior is well covered. The description adds value beyond the schema without contradicting any 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?

Two sentences, front-loaded with the primary purpose and output format. Every clause adds value: the diff description, the labelling detail, the companion reference, and the limit clamp. No wasted words.

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?

Without an output schema, the description conveys what the agent can expect: a plain-text diff with labelled sides and a line limit. It covers the main inputs and their source. It does not specify error behavior (e.g., missing revisions) or pagination beyond the limit, but for a diff tool this is adequate. The description is sufficient for an agent to call the tool correctly.

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 parameters are already documented. The description adds extra meaning: it clarifies that rev_from is the older revision and rev_to the newer (also in schema), explains the limit default and max (also in schema), and tells the agent to obtain revision IDs from `revisions`. This goes beyond the schema's bare descriptions, so a score above the baseline is warranted.

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 explicitly states the verb 'compare' with the resource 'revisions' and explains the output is a plain-text unified diff. It clearly distinguishes itself from the sibling tool `revisions` by framing itself as the edit-auditing companion. The purpose is specific and unambiguous.

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?

It explicitly names the sibling `revisions` and provides concrete use cases: 'see what a specific edit added or removed, review edits before trusting a new paragraph, or spot stealth rewrites.' It also tells the agent where to get revision IDs ('get revision IDs from `revisions`'), giving clear when-to-use guidance.

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