Claude Code / Codex speed and accuracy drift

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

Annotations already cover readOnly/idempotent/openWorld, but the description adds non-obvious operational context: hourly measurement from a single EU server and one account per vendor, the 24h-vs-7day window with Mann-Whitney significance flags, and the fixed hard-question accuracy panel. It also discloses the vantage-point limitation, which an agent needs to interpret results honestly.

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?

Three dense but front-loaded sentences: purpose and metrics first, then the usage trigger, then the caveat and alternative. Every sentence carries weight, though the metric list is long enough to flirt with over-specification.

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?

With an output schema present and annotations covering safety, the description still supplies the measurement methodology, comparison window and statistical method needed to interpret the return values correctly. Nothing material to correct invocation is missing.

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% and the single enum parameter already documents both values plus the omit-for-both behavior. The description adds no parameter syntax beyond that, so the baseline 3 applies.

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 precise verb+resource ('Report whether the Claude Code or Codex CLI coding agents got slower, think less or answer worse than their own recent baseline') and enumerates the exact metrics returned. It also explicitly separates itself from sibling get_ai_api_latency for raw API latency.

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?

Gives an explicit trigger phrase ('Use it when someone asks is Claude Code slow / nerfed today') and an explicit alternative condition ('for raw API latency use get_ai_api_latency'). This is exactly the when/when-not/alternative pattern.

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