record_decision

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

With no annotations, the description carries full burden. It states the data is stored in episodic memory, retrievable via episodic_search, and the return format. It does not disclose idempotency, overwrite behavior, or side effects, but covers basic behavioral aspects.

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 four sentences, front-loaded with the purpose, then storage info, usage guidelines, and return format. Every sentence is necessary, no wasted words.

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?

The tool has 4 parameters, 1 required, no output schema. The description provides return format but lacks full parameter explanation. It differentiates from routine changes but not explicitly from similar sibling tools like log_episode or store_memory.

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 description should compensate. The description explains 'summary' and 'rationale' implicitly but does not mention 'affected_files' or 'repo_path'. Adds some value but not comprehensive.

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 clearly states the tool records architectural decisions, bug fix rationales, or 'why we did X'. It specifies the verb 'Record' and the resources, and distinguishes from routine changes by emphasizing non-obvious decisions.

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 explicitly says when to call (non-obvious decisions, bug root-causes, user requests to remember) and when not to call (routine changes). It does not name alternative tools but provides clear context for usage.

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