sort

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

Consistent with readOnlyHint annotation, adds 'Read-only, no side effects,' and details about deterministic behavior, tie-breaking, and output formats.

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 sentences front-loaded with core purpose, no fluff, every sentence adds value.

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?

Covers output format, usage scenarios, and limitations (deterministic tie-breaking, unique behavior). Lacks mention of max_lines truncation and encoding handling, but schema fills some gaps.

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 has 100% coverage with descriptions; the tool description adds high-level context for some parameters (numeric, reverse, unique, raw) but does not fully cover all eight parameters.

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?

Clearly states 'Sort text lines deterministically from files or stdin.' Provides specific examples of options and distinguishes from siblings like 'shuf' and 'uniq'.

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 states when to use (order data for downstream processing) and when not to (not for deduplication of non-sorted data, not for randomizing), with alternative tool names.

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