brain_recommend

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses that the tool is read-only, deterministic, rule-based (not a model), that every candidate cites its source tool and number, that per-source health is reported to prevent degraded evidence from appearing supportive, and that the output includes a reasoning contract for the calling model. These behavioral details go well beyond what annotations would need to cover.

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 three dense but purposeful sentences. It front-loads the primary function, then explains the deterministic nature with evidence tracing, and finally describes the output contract. Every sentence adds substantial value with no filler or redundancy.

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, the absence of annotations, and the lack of an output schema, the description is remarkably complete. It explains the tool's scope, parameter behavior, evaluation approach, evidence-integrity safeguards, and the reasoning contract expected of the caller. It provides enough context for an agent to select and invoke the tool correctly and to interpret its output.

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?

The schema has one optional boolean parameter, 'deep', with zero schema-level documentation. The description fully compensates by explaining that 'deep: true' adds the roadmap scan. This adds clear meaning to the only parameter, and no other parameters exist to be undocumented.

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 opens with a specific verb and resource: 'Rank next steps from the brain's own read-only evidence.' It clearly distinguishes itself from sibling tools, which are individual source viewers (backlog, analytics, etc.), by positioning this as a cross-source ranking/decision tool. It also clarifies that it is deterministic and NOT a model, preventing semantic confusion.

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 clearly implies when to use this tool: when next-step recommendations need to be generated from available brain evidence. It also explains the optional 'deep: true' parameter for including roadmap scans. However, it does not explicitly state when not to use it or name alternative tools for specific situations, though the sibling list makes this fairly obvious.

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