diagnose_crash

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

With no annotations provided, the description takes full responsibility for behavioral disclosure. It explicitly states that it 'never changes any file', that findings are 'ADVISORY ONLY', and details the exact output structure (ranked findings, evidence lines, environment and load-order dicts). It also discloses the default behavior when path is omitted.

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 structured with a lead phrase followed by a clear breakdown of pipeline steps and outputs. It's about 100 words, which is appropriate for a tool that orchestrates multiple subsystems. Every sentence adds useful information, though a slight tightening could push it to 5.

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 that there is no output schema and no annotations, the description covers all required aspects: what it does, what it returns (including ranking criteria), what is safe (no file changes), and how the optional parameter behaves. It is fully complete for an orchestration tool.

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 only parameter `path` is not described in the schema (coverage 0%), so the description's clarification that it parses the given log or defaults to the newest one fully compensates. This is the key semantic information the agent needs to invoke the tool correctly.

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 'One-shot crash diagnosis: parse log + scan environment + match signatures' which clearly states the tool's action and scope. It distinguishes from sibling tools by describing the full pipeline, not just individual steps like list_crash_logs or get_load_order.

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 the comprehensive nature of this tool versus the individual sibling tools, and clarifies that it can use an explicit path or default to the newest log. However, it doesn't explicitly say when to use it instead of the simpler tools, such as 'if you only need a single file, use get_crash_log'. That nuance prevents a 5.

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