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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, but the description still adds meaningful behavior: it does not change the project head, and it prefers a stored parent-to-child diff over comparing summaries. It stops short of describing the response shape beyond 'Returns diff.'

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?

Front-loaded with the core action and scope, then alternatives, then mechanism. Four sentences, little waste; only 'Returns diff.' is nearly redundant, adding minimal information.

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?

For a read-only comparison tool with no output schema, the description conveys scope, safety, alternatives, and diff strategy. The return value could be fleshed out further, but the essential calling context is present.

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%, so both revision parameters and projectId are already documented in the schema; the description adds no syntax or ordering detail beyond what is there. Baseline 3 is appropriate.

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+resource ('Compare two revisions') and immediately scopes it to reviewing or undoing scene changes, which lets an agent distinguish it from sibling mutation tools like revision_restore.

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 and its condition ('Use revision_restore only to replace the current scene with an earlier revision') and points to project_get for obtaining revision IDs, so when-to-use and when-not-to-use are both covered.

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