rlm_decision_supersede

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

With no annotations, the description must fully disclose behavior. It mentions the old decision is marked SUPERSEDED and linked, but does not specify whether this is destructive, what permissions are needed, or what the return value is. It also doesn't mention if the new decision is immediately active or any potential conflicts.

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 short paragraphs, front-loaded with the core action. Every sentence adds value without redundancy. It is efficient and easy to scan.

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?

For a tool with 11 parameters (6 required) and no output schema, the description covers the main purpose and state changes adequately but lacks details on side effects, error conditions, or post-call state. The schema fully documents parameters, but behavioral completeness is moderate.

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 100%, so baseline is 3. The description does not add any extra meaning beyond the parameter names and types in the schema. It provides no examples, relationships, or formatting hints.

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tool 'supersedes an existing decision with a new one' and specifies the behavioral effect: the old decision is marked SUPERSEDED with a link to the new one. This differentiates it from siblings like rlm_decision_create (which likely creates independent decisions) and rlm_decision_query (which queries).

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 when replacing an existing decision while keeping history. However, it does not explicitly state when not to use (e.g., if no existing decision) or contrast with alternatives like rlm_decision_create. It also lacks preconditions, such as requiring the old_decision_id to exist.

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