get_diff

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

With no annotations, the description carries the full burden and does well: it discloses return semantics beyond structure, explaining that a statistic with no drift event did not change and that unevaluated_tables means the table was not compared. Pagination behavior ('changes is paged in recorded order with total and next_cursor; every other key rides the first page whole') is also disclosed, though permissions/auth and error behavior are not.

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 the core purpose, then structured as return-shape, edge-case semantics, pagination, and sibling boundary. Sentences are dense and clause-heavy but each carries distinct information, and there is no filler.

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?

No output schema exists, so the description must explain the return document, and it does: summary, changes, total, next_cursor, and the unevaluated_tables caveat. For a read-only paged diff tool this is close to complete, missing only failure/auth context.

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 the schema already documents kind, table, cursor and connection. The description's cursor/connection remarks largely restate the schema descriptions, adding little beyond them, so the baseline of 3 applies.

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?

The description names a specific verb+resource ('what changed between the database's last two prints') and unambiguously scopes it as a diff over recorded changes rather than current state. It explicitly draws the boundary with the sibling get_table_context, so an agent can distinguish the two without opening either schema.

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?

It states when this tool is the right answer (you want what changed, not current state) and names the alternative (get_table_context) with the condition that selects it. It stops short of covering the remaining siblings or stating explicit when-not conditions, but the routing guidance is clear.

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