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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real domain behavior: absence of observation is not treated as reinstatement, and enrichment-only changes are filtered out. That filtering semantics is genuinely useful information an agent would not get from annotations or schema.

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 short sentences with the core operation front-loaded and no filler. It is efficient, though the extreme brevity borders on under-specification for a comparison tool.

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?

An output schema exists so return values need not be explained, and annotations cover safety. However, the description never clarifies what a retained snapshot/generation is, how to obtain the required from_generation UUID, or pagination behavior, leaving meaningful gaps for a tool with four parameters.

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 from_generation, to_generation, cursor, and limit are already documented in the schema. The description adds no additional meaning about how snapshots map to parameters, so the baseline 3 applies.

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 states a specific verb and object ("Compare two retained snapshots"), but the resource is described only as generic snapshots rather than exclusions, and it does nothing to separate itself from close siblings like exclusion_context, check_exclusions, or search_exclusions. An agent can grasp the operation but cannot confidently route to this tool over its siblings.

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?

There is no statement of when to use this tool, what prerequisites exist (e.g. needing generation UUIDs), or which sibling to prefer instead. The caveats given are about result semantics, not about selection among the many exclusion-related siblings.

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