Recent writes

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is settled; the description still adds real value by disclosing ordering, per-entry payload, the fact that entries correspond to what undo_last_write reverts, and the omission of external/manual edits. It stops short of covering limit/truncation behavior when more writes exist than the requested count.

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?

Four short sentences, front-loaded with the core identity, then contents, then usage, then the scope caveat. No redundancy with the title or schema; every sentence adds new 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 simple, annotation-covered read tool with an output schema and a fully described single parameter, the description supplies everything an agent needs: what it returns, ordering, how to use it, and its blind spot. Nothing material is missing.

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?

The single limit parameter is already fully documented in the schema (min 1, max 200, default 10), so the schema carries the semantics. The description says "newest first" but never mentions how the limit interacts with ordering or what happens when the limit truncates history — 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 and resource — an audit log of this server's writes to the tracker — plus ordering (newest first) and per-entry contents (time, tool, row, backup file, changed cells with old/new values). This clearly separates it from generic read siblings like get_application or summary.

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 explicit use cases ("answer 'what did you change?' or to check that a write landed"), names the related tool it feeds (undo_last_write would revert these entries), and states an exclusion: manual edits in Excel or Sheets are not captured. When-to-use, relationship, and scope boundary are all covered.

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