Open-Brain

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

No annotations are provided, so the description carries full burden. It discloses the computation formula but doesn't mention behavioral traits: whether this is a read-only or mutating operation (likely mutating given 'Recompute'), performance impact (e.g., resource-intensive), side effects (e.g., updates existing scores), or error conditions. For a tool with zero annotation coverage, this is a significant gap.

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 a single, efficient sentence that front-loads the key action ('Recompute salience scores') and provides essential detail (the formula) without waste. Every word earns its place, making it highly concise and well-structured for quick understanding.

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 has 0 parameters and no output schema, the description is minimally complete: it states the purpose and formula. However, for a likely mutating operation with no annotations, it should disclose more behavioral context (e.g., what gets updated, performance). The formula detail helps, but gaps in usage and transparency reduce completeness.

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 tool has 0 parameters, and schema description coverage is 100% (though schema allows any properties). The description doesn't need to explain parameters, and it adds value by specifying the salience formula components (recency, access, links, merges, source), which clarifies what 'salience scores' entail beyond the tool name. This compensates for the lack of parameter documentation.

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 action ('Recompute') and the target ('salience scores'), with a specific formula provided (recency × access × links × merges × source). It distinguishes from siblings like 'thought_stats' or 'review_stale' by focusing on recomputation rather than retrieval or review. However, it doesn't explicitly differentiate from all siblings (e.g., 'pipeline' might also involve computation).

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?

No guidance is provided on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., when salience scores become stale), exclusions (e.g., not for real-time updates), or related tools like 'review_stale' or 'thought_stats' that might overlap. The description implies usage for recomputation but lacks contextual boundaries.

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