List this session's writes

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

Annotations only declare readOnlyHint=true; the description adds the crucial behavioral facts that the ledger is in-memory, starts empty after a server restart, and that backups persist on disk anyway. It also discloses ordering (newest first) and the backup-per-entry payload, which no structured field conveys.

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, front-loaded with the core purpose and scope before the memory/persistence caveat. Every clause carries load: ordering, revertable backups, relationship to undo_writes, and the restart caveat.

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 no output schema, the description usefully describes the return shape (files plus their backups, newest first) and the persistence caveat. The only gap is that the limit parameter governing result size is left unexplained.

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 has 0% schema description coverage and is not mentioned anywhere in the description, so there is no guidance on its purpose, default, or 1-200 bound. Only the implicit 'newest first' hints at ordering; the parameter itself is undocumented.

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: every file this server process has written, ordered newest first, each with its revertable backup. It explicitly differentiates itself from siblings, calling out that it is the ledger undo_writes steps through and that list_backups sees the on-disk files instead.

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?

Clearly positions the tool against undo_writes (which steps through this ledger) and list_backups (which reads backups on disk), so the agent can infer when each is appropriate. It stops short of an explicit 'use this when / do not use when' statement, but the routing context is strong.

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