analyze_perf

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

Annotations already declare readOnlyHint=true, etc. The description adds valuable behavioral details: output structure, sorting order, source of data (session ring vs DB), and the requirement for telemetry.enabled for persistent windows. It also introduces the TOON output format and its benefits.

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 two sentences, front-loading the purpose, and each sentence adds essential information without redundancy. It efficiently covers behavior, parameters, and output without wasted words.

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?

Given no output schema, the description provides a detailed output structure. It covers parameters, sources, and conditions. However, it does not explicitly state that 'tool' is required (as per schema), which could slightly reduce completeness for an agent.

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% coverage, and the description adds meaning for each parameter: it explains the default for window, the behavior of output_format options (including token savings for TOON), and the filtering purpose of tool. This goes beyond the schema descriptions.

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 states 'Per-tool latency telemetry: p50/p95/max, count, error_rate.' It specifies a specific verb (analyze) and resource (latency telemetry), and distinguishes itself from sibling tools by focusing on performance data with sorting by p95 descending.

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 explains when to use different window options ('Default reads the current session ring; window=1h|24h|7d|all reads from persistent DB') and mentions the prerequisite (telemetry.enabled). It does not explicitly state when not to use or compare to alternatives, but context is clear.

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