get_klipper_log

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered, and the description usefully adds that output is 'truncated to a byte budget' — a real behavioral trait an agent must know. However, it never discloses what other logs the 'which' parameter can address or what happens when the budget cuts the tail, which matters for a diagnostics tool.

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?

Two sentences, front-loaded with the resource and the diagnostic value, ending with the one operational constraint. No redundant restatement of the tool name and nothing that could be cut without losing information.

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?

An output schema exists, so return-format explanation is unnecessary, and truncation is disclosed, which covers the main surprise factor. What remains missing is any guidance on the 'which' selector and reasonable byte budgets, which is material for a tool whose schema documents neither parameter.

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%, so the description must carry parameter meaning, and it only half does: 'truncated to a byte budget' implies max_bytes behavior without naming it or its tradeoff. The 'which' parameter is entirely unexplained — the text implies only klippy.log, yet the parameter's default and presence suggest other log sources, leaving an agent unable to use it 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?

States a specific verb and resource ('Read the tail of klippy.log') and pins down the diagnostic questions it answers (shutdown cause, MCU error, failed print report), which separates it from the sibling get_gcode_log by subject matter. It stops short of explicitly naming that sibling as the alternative for gcode traffic, so the differentiation is implied rather than stated.

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 clear when-to-use context by enumerating the diagnostic scenarios (why Klipper shut down, MCU error cause, failed print reports) and calls itself the 'definitive place' for them. No exclusions or explicit 'use X instead' routing is provided for the log-reading siblings, so it falls short of full alternative guidance.

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