get_latency_analytics

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the read-only/idempotent behavior is covered. The description adds genuinely useful behavioral context beyond annotations by disclosing Enterprise gating and the 403 failure mode on non-Enterprise plans. This is a meaningful behavioral disclosure not present in the 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, with three sentences each serving a distinct purpose: what it returns, when to use it versus an alternative, and an important access constraint. The core purpose is front-loaded before the sibling distinction, and no sentences are wasted.

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 analytics tool with a rich output schema, annotations covering safety, and a fully-documented input schema, the description covers the key contextual gaps: the specific latency metrics, the sibling distinction, and the Enterprise restriction. It could be more complete by noting pagination or summary statistics availability, but the output schema likely covers return structure.

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 baseline for this dimension is 3. The description names key metrics returned but does not add substantial meaning to the 29 parameters beyond what the schema already documents. The required time_of_generation_min/max parameters are not elaborated in the description, though the schema covers their format.

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 clearly identifies the tool as retrieving latency time-series data and enumerates the specific metrics included (avg, p50, p90, p99, per-bucket). It also names the sibling tool get_cache_hit_latency and distinguishes it by scope, which prevents confusion with the many other analytics tools in the sibling list.

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?

The description explicitly says to use this tool to 'spot slowdowns and regressions' and directs users to use get_cache_hit_latency 'when you only want cache-hit latency'. This provides both a positive use case and an exclusion criterion naming the alternative, which is especially valuable given the large cluster of latency-related siblings.

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