get_retry_amplification

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

With no annotations at all, the description carries the full burden and does substantial work: it defines the diagnostic signal (per-client load rising with latency, errors or churn while client count stays flat) and states the state machine concepts (armed baseline, candidate vs amplifying episode). It does not state access requirements or whether the read is expensive/live-polling, which keeps it from a 5.

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?

Two sentences, front-loaded with the resource and content of the response, followed by the usage trigger. The first sentence is long and stacks a parenthetical definition plus a list, but every clause carries information; nothing is 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 and no annotations exist, so the description must explain the return payload, and it does so thoroughly enough that an agent knows what fields to expect. Missing are any notes on freshness/live-update behavior or the meaning of 'armed' beyond naming it, which for a live detector tool would be the final 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?

There is a single optional parameter, instanceId, and the schema already documents it at 100% coverage. The description adds nothing about how the instance override interacts with the selected connection, so it neither helps nor misleads beyond the schema baseline.

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 opens with a specific verb and resource ('Get the live retry-amplification detector state') and enumerates exactly what that state contains: baseline armed, open candidate/amplifying episode, last episode and trigger, and top-growing clients. It is clear what the tool returns, though it never names the neighbouring diagnostic tools (get_anomalies, get_latency_regressions) it might be confused with.

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 gives a concrete selecting condition: 'Use when an incident looks like a self-sustaining retry storm rather than real traffic growth.' That implicitly excludes ordinary traffic-growth investigations, but no sibling tool is named as the alternative for those cases, so the routing is suggestive rather than explicit.

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