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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, yet the description adds substantial context beyond them: entries are per user, retained only for the days set by the policy's answers.historyDays, and can be forgotten via the portal Usage page. It also discloses that some entries store numbers while others store only a per-cell hash, which explains why a comparison may be limited.

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?

The dual-mode behavior is front-loaded in the first sentence, followed by retention and usage. It is dense and the first sentence is long, but every clause carries information; only the slight run-on quality keeps it from a 5.

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 carries the burden of explaining returns and does so: it enumerates the listed fields and states that the comparison reports whether numbers changed and which cells. Retention policy and per-user scoping round out what an agent needs to call it and interpret results correctly.

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%, so the baseline is 3, but the description adds genuine meaning the schema does not: the two parameters are really two modes — limit lists newest-first, and supplying a fingerprint switches to re-read-and-compare. That mode-switching semantics is the key thing an agent needs and is not in the schema.

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+resource (lists remembered data slices) and explicitly describes the second mode: given a fingerprint, it re-reads that slice from Oracle and reports whether numbers changed. The enumerated per-entry fields (connection, application, cube, point of view, read time, cell count, stored vs hash) make the resource concrete and distinguishable from any sibling.

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 triggers: when the user asks what a slice showed before, whether numbers moved since an earlier answer, or to compare today's read with a remembered one. No sibling is named as an alternative or exclusion, which keeps it short of a 5, but the usage context is clear enough that an agent will pick it over export_data_slice or get_job_status.

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