get_cdc_report

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

No annotations are present, so the description carries the full burden. It discloses counting semantics, no double counting, non-signoff guarantees, that empty results are not CDC-clean, and explicitly states the tool does not modify constraints.

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?

Front-loaded purpose, then invocation modes, caveats, and parameters. Every sentence adds distinct value, including safety and semantic warnings; there is no filler or repetition.

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, return-value documentation is not needed. The description fully covers limits, caveats, and invocation modes, but it does not explicitly state whether session_id and report_file are mutually exclusive or what happens if neither is provided, leaving minor invocation ambiguity.

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 0%, but the description's Args section fully compensates: session_id, report_file (optional, raw text, 16 MiB limit, no session needed), and max_details (0..500, truncation behavior). This adds meaning beyond names and defaults.

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?

Description opens with a specific verb and resource: '解析 CDC 报告' and states exact outputs: counts by clock pair, severity, rule, and bounded detail JSON. This clearly distinguishes it from timing, IO, and utilization report siblings.

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?

Explicitly describes two invocation modes: live via a session executing report_cdc -details -return_string, and offline via a raw report file requiring no session. Clear context is provided, though no explicit 'use this instead of X' alternatives are named.

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