recent_changes

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds genuinely useful context: ordering ("newest last") and scope (only changes this server made, per session). It does not address retention/backfill limits, whether the log survives across sessions, or how one would actually perform the "undo" it mentions, so with annotation coverage the extra context is helpful but not rich.

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, zero waste, and the ordering fact ("newest last") is stated up front alongside the scope. The parenthetical category list is compact and each item adds discriminating information about what counts as a change.

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 simple two-optional-parameter read tool with no output schema, the description covers what it is and when to reach for it, but nothing about the shape of a returned entry (what fields identify a change, whether there is a change ID an undo flow would need). An agent wanting to act on the result must probe the response blind.

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 parameters (limit, account) are already documented in the schema and the baseline is 3. The description adds no extra meaning about paging past the limit or how the account filter interacts with the server-wide log, so it neither compensates nor detracts.

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?

Specific verb+resource ("Shows the latest changes this server made") with an enumerated list of change categories (labels, archiving, filters, drafts, signature, saved files) that pins down the resource. It is distinguishable from listing siblings like list_drafts or list_labels because it is an audit trail of mutations rather than a current-state listing, though it never names that contrast explicitly.

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?

"Use it to review or undo what happened in a session" gives an implied when-to-use: after making changes, to inspect or revert them. There is no explicit exclusion or named alternative (e.g., use list_labels to see current labels vs. this tool to see label changes), so the agent must infer the boundary itself.

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