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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds scope (only 'your own charm's shared data'), the record shape (writes, deletes, actor, diff), and the supported filters, which is useful context beyond the structured fields.

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 compact sentences: the first front-loads what the tool returns, the second carries filters and the recommended usage. No filler, and the routing hint sits at the end where it belongs.

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?

With read-only annotations, a fully documented schema, and no output schema, the description covers purpose, scope, filters, and follow-up adequately. Minor gaps remain, such as ordering/pagination behavior, which is only implied by the limit parameter's 'newest first' note in the schema.

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 the schema already documents all six parameters including defaults and the writer format. The description names only key, writer, and since, with no syntax or meaning beyond what the schema provides, so the baseline of 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?

States a specific verb and resource ('Read the change history of your own charm's shared data') and enumerates what the record contains: every write and delete, who did it, and what changed. This clearly separates it from siblings like read_app_data (current state) and rollback_app_data (reversal).

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 workflow condition and the alternative: 'Use it to see vandalism before undoing it with rollback_app_data.' That gives an agent a concrete when-to-use and the natural follow-up tool, though it does not state when this tool should be avoided.

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