Get recent changes

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

The annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds valuable context beyond those: it scans all non-private metrics, and it includes a privacy note that returned data becomes part of the model conversation. It doesn't cover every possible behavioral trait, but it goes well beyond the structured fields.

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 description is front-loaded with the core purpose and never repeats the title. Every section earns its place: purpose, when-to-use, when-not-to-use with a named alternative, and a meaningful privacy caveat. It is longer than average, but the length is justified by actionable content rather than 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?

For a read-only scanning tool with a single optional parameter and an output schema, the description covers everything needed for correct selection and invocation: what it scans, how windows are defined, when to prefer it, when to avoid it, and a privacy consideration. The output schema can carry return-format details, so their absence here is not a gap.

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 fully documents the days parameter and the 4x comparison window. The description reinforces the same semantics without adding new parameter-level meaning. Baseline 3 is appropriate here because the structured schema does the heavy lifting.

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 ('scan'), the resource ('every non-private metric'), and the exact analysis performed (period-over-period shift, anomalies, trend). It also explicitly differentiates itself from sibling per-metric tools like explain_metric_change, so an agent can tell when this is the cross-metric overview versus a targeted analysis.

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 the ideal use case: starting a 'how have I been doing?' conversation across all metrics. It also gives an explicit exclusion: if the user named a specific metric and wants the full why-bundle, use explain_metric_change instead. This gives clear routing guidance beyond what the schema or annotations provide.

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