diagnose_slow_requests

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does a good job by listing what the tool examines across multiple layers (GC, connection pool, thread pool/locks, downstreams, proxy timeouts), giving an agent an accurate picture of scope. It does not state whether it is read-only or how results are structured, but for a diagnostics tool the coverage enumeration provides solid transparency.

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?

A single dense sentence front-loads the purpose ('RUNBOOK for latency') and then packs the coverage areas into a comma-separated list. The proxy_service guidance is placed last, which is slightly off as it is an important conditional, but overall there is no wasted text.

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?

This is a complex runbook-style diagnostic with no output schema and no annotations, so the description must compensate. The enumerated coverage areas are informative, but the description does not clarify what the runbook returns (a report? structured findings?), how to proceed through steps, or what output shape an agent should expect. For a tool of this complexity, the description is adequate but leaves the output contract unstated.

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 75%, so the schema already documents service, window, and namespace. The description adds genuine meaning to proxy_service, which has no schema description, by explaining it switches to the user-facing view. However, it does not elaborate on window format or the interplay of the parameters beyond the schema, so it adds value only marginally above 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 leads with 'RUNBOOK for latency' and enumerates the exact analysis dimensions (per-endpoint latency, throttling, GC, connection pool, thread pool/locks, downstreams, proxy timeouts). This clearly distinguishes it from narrow siblings like get_endpoint_metrics, get_thread_dump_summary, and get_connection_pool_status, which each cover only one slice, while diagnose_slow_requests is the aggregate diagnostic.

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 conveys that this is a runbook for latency diagnosis, which implies it is the first stop when requests are slow, but it never explicitly says when not to use it or names alternative tools (e.g., find_slow_traces for trace-level, diagnose_service for a broader service check). The proxy_service hint ('for the user-facing view') is the only conditional routing guidance present.

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