Get Recent Changes

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

Annotations already declare readOnly/non-destructive, and the description adds substantial behavior beyond that: newest-first ordering, per-transaction truncation at 10 objects with a remainder count, how added/removed links are rendered as Reference, and the hard 100-transaction ceiling that puts older history out of reach.

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 what it returns, then scope limits, then routing to siblings — a logical order with little waste. It is a dense single block with long clauses, so it is slightly harder to scan than it could be, but nearly every sentence carries 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?

There is no output schema, so the description carries the return-shape burden and does so thoroughly: per-transaction fields, per-object fields, truncation behavior, and reference encoding. An agent has everything needed to call it and interpret results.

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% and already documents the 1–100 range, default 20, and clamping. The description still adds meaning the schema lacks: limit counts transactions, not objects, which is the key semantic an agent could get wrong.

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?

Opens with a specific verb and resource ('Show the tree's recent edit history, newest first') and immediately enumerates the fields returned. It is clearly distinguishable from siblings like get_timeline (dated events for one person) and list_objects (sorted record lists).

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 ('check that your own writes landed', 'find the number undo_change takes') and names alternatives with the conditions that select them: list_objects with sort -change for older history, get_timeline for per-person dated events, get_object to read a changed record.

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