rlm_end_of_task_commit

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

With no annotations provided, the description explains it extracts specific content while filtering operational receipts, but lacks details on mutation behavior (e.g., idempotency, overwrite), auth requirements, or rate limits, which are crucial for an agent.

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 two concise sentences, front-loaded with the primary action and purpose, with no superfluous 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?

Given the tool's complexity with 8 parameters, no output schema, and no annotations, the description fails to cover return values, error handling, prerequisites, or behavioral details like whether commit is idempotent, making it insufficient for complete understanding.

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 coverage is low (25%), and the description only adds context for persist_types (mapping to 'decisions, learnings, preferences, todo, context, workflow'). Other parameters like outcome, files_touched, artifacts, category, external_user_id, and dry_run are left unexplained, leaving significant gaps.

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?

Description clearly states the tool persists durable outcomes from task summaries into memory, specifying the types of information extracted (decisions, learnings, etc.) and explicitly excluding source documents and specs, thus distinguishing it from siblings like rlm_store_summary or rlm_remember.

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 implies usage for task outcomes and excludes source documents/specs, but does not explicitly compare to other memory tools or state when to prefer this over alternatives, leaving the agent to infer context.

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