flatten_messages

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

Discloses key behaviors: purely functional, no mutation, no disk/network, same engine as library. With no annotations, it covers essential traits, though could mention error handling or size limits.

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?

Description is thorough but slightly verbose; includes some redundant phrasing. Front-loads core action ('flatten a raw Anthropic Messages API messages[] array in memory'), but could be tightened.

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?

Missing output schema means description should explain return format (e.g., structure of 'extracted'). It mentions markers and originals but not the exact shape, leaving some ambiguity for the 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?

Schema already describes both parameters (100% coverage). Description adds context about Anthropic Messages API, tool_result blocks, and the effect of min_size threshold, adding meaning beyond the schema.

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 it flattens raw Anthropic Messages API messages[] array in memory, swapping bulky tool_result blocks with markers. Distinguishes from siblings like unflatten_messages and flatten_session.

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 tells when to use (in-memory flattening) and when not ('for production use inside your own process, prefer importing the library'). Also states to persist 'extracted' and feed to unflatten_messages, providing clear usage pattern.

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