get_cache_summary

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's extra value is the enterprise plan restriction and the 403 error on non-Enterprise plans, plus the aggregate-not-time-series behavior. No contradiction with annotations.

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 compact and front-loads the enterprise restriction, but 'Enterprise-gated.' is repeated verbatim, which is avoidable waste. Otherwise the sentences are short and information-dense.

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 complex 29-parameter tool, the description covers the essential selection facts: single-workspace aggregate, time range, returned metrics, the alternative tool category, and plan-based auth failure. With a full output schema and 100% schema parameter coverage, the remaining optional filters do not need to be restated in prose.

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 input schema has 100% parameter descriptions, so the baseline is 3. The description only names the high-level workspace/time-range scope and does not add meaning beyond what the schema already states for the 29 parameters.

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 ('Get cache summary metrics') and names the scope ('one workspace and time range') and the concrete metrics returned (hits, average cache-hit latency, total requests, percentage speedup). It also distinguishes itself from 'graph cache tools' by offering a single aggregate instead of changes over time.

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?

Provides an explicit routing rule: use the graph cache tools when changes over time are needed instead of a single aggregate. The alternative is somewhat generic ('graph cache tools') rather than naming exact sibling tools, and it does not mention other analytic siblings like get_cache_hit_rate, so it is clear but not exhaustive.

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