brain_reframe

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

With no annotations, the description carries full burden. It discloses that priority/evidence/title/why/action/systems/phases are server-side derived and never accepted from the caller, and that the output is a reasoning contract the calling model must execute to answer lens questions and emit a verdict. This is significant behavioral transparency, though it doesn't mention read-only status or error conditions.

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 sentences, front-loaded with the primary action. Every clause contributes: the input modes, the server-side derivation constraint, the output contract, and the caller's expected execution. No filler.

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 complex tool with nested anyOf and no output schema, the description explains the core purpose, input alternatives, server-side constraints, and the nature of the output (reasoning contract with verdict). It lacks specifics about the reasoning contract's structure or error cases, but it covers the essential contextual need.

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 the description must compensate. It explicitly names `recommendationKey` as the lookup key and describes `taskContext` as a bounded task-only subject alternative. It also clarifies that certain fields are never accepted. However, it doesn't explain the individual properties of taskContext or the `lens` enum values, leaving the agent to rely on schema enums. Partial compensation.

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 uses a specific verb ('Reframe') and identifies the resource ('a real brain_recommend recommendation ... through a reasoning lens'). It also distinguishes from siblings by explaining the alternative task-only input and the server-side derivation, clearly differentiating from tools like brain_recommend and brain_lenses.

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?

It states when to use the tool: when you have a recommendationKey or a bounded task-only subject. It also explains that priority/evidence/etc are derived server-side, so the caller should not provide them. It doesn't explicitly name alternative tools or exclusions, but the context makes the usage context clear.

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