What changed in this file

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

Annotations already declare readOnly/destructive=false, and the description repeats 'Reads only'. It earns credit for genuinely new behavior: the journal lives in this server process and 'a restart starts it empty' (volatility), how a change counts as 'yours' versus a collaborator's, what a conflict is, and which editors are verified (Design) versus unverified (FigJam, Slides). Return-shape detail is also given where no output schema exists.

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 purpose, and most sentences carry real information, but it collapses the journal entry shape, plugin fields, parameter notes, volatility, and editor support into one dense paragraph. Clauses like 'one that leaves a node as you last wrote or read it is yours, however late' take effort to parse and would read better as structure.

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?

There is no output schema, so the description must carry the return contract – and it does, enumerating journal entry fields (seq, at, tool, summary, ok, error, created, targets, rolledBack) and the plugin payload. Combined with volatility disclosure and editor coverage, an agent has everything needed to call and interpret it.

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 the baseline is 3. The description restates the same semantics the schema already carries – `since` accepts a seq ("12") or a savepoint id ("sp-3"), `limit` is the newest calls defaulting to 100 – rather than adding new meaning. The `session` parameter is not addressed at all in the description.

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 resource: the change view of a file, split into the server-side write `journal` and the plugin-side `changes`/`conflicts`/`pageSwitches`. That is well beyond a restatement of the name, and it is distinguishable from `figma_savepoint`/`figma_rollback`. It never explicitly contrasts itself with those siblings, which keeps it out of the 5 tier.

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?

Gives clear usage context: 'what you report at the end of an instruction, and what a person reads to review your work' – an agent knows this is the wrap-up/reporting call. It also implicitly routes `since`/`limit`/`savepoints` to their purposes. No explicit when-not-to-use or named alternative is given.

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