review_beliefs

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 excellently: it explicitly declares 'Read-only — it suggests, never deletes.' It also details the types of staleness it detects, giving the user a full understanding of what will happen.

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 concise but information-dense, starting with the main purpose, then the criteria, then the side-effect guarantee and the confirmation action, followed by the arg. Each sentence contributes meaning without 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?

For a low-complexity tool with one optional parameter and an output schema, the description covers all necessary aspects: purpose, usage context, parameter semantics, and behavioral transparency. The output format is conveyed by the output schema, so no further description is needed.

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 provides only the parameter name and type with default null. The description adds crucial semantics: 'Scope to a project (None = whole brain).' This fully explains the meaning and usage of the only parameter, compensating for the 0% schema coverage.

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 states the tool scans the brain for memories that are likely stale and need review, specifying exact criteria (superseded, past deadline, conditional, flagged). It clearly distinguishes itself from siblings like recall or list_memories by focusing on review/suggestion rather than retrieval or modification.

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 provides clear context for when to use the tool: to find stale memories that need review. It also indicates the read-only nature and suggests using flag_stale to confirm. However, it does not explicitly mention when not to use it or recommend an alternative tool (e.g., review_procedures for procedures), so it lacks explicit exclusion criteria.

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