memory_world_search

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

Annotations already cover the safety profile (readOnly, non-destructive, non-idempotent), yet the description adds real behavioral context beyond them: entries carry an age-decayed effective_confidence, a stale flag that means 're-verify before relying on it', and source_url/source_quote for citation. Those reliability semantics are the kind of thing an agent cannot infer from structured fields alone; only the return-shape line is somewhat redundant.

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?

Front-loaded with purpose and the usage trigger, then a compact disclosure of entry metadata. The trailing 'Returns: {count, entries}' line is largely wasted given a machine-readable output schema exists, but overall the text is tight with no padding.

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 read-only similarity search with full schema coverage, annotations, and an output schema, the description supplies everything else the agent needs: when to reach for it, what makes results trustworthy (confidence decay, stale flag), and how to cite them. No material gaps remain.

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% — query, top_k and verbose are each documented in the schema. The description adds no parameter-level detail (no guidance on top_k sizing or when verbose is worth it), so the schema does all the work; baseline 3 is correct.

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?

States a specific verb and resource ('Search current WORLD facts ... by similarity') and disambiguates the data pool with the parenthetical '(sourced external knowledge)'. That qualifier separates it from generic memory_search / memory_recall / document_search without the agent needing to open sibling schemas.

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?

Gives a clear triggering condition: 'Use when a task turns on an external fact your training data may be stale.' It does not name alternatives (e.g. memory_search for personal memory, document_search for uploaded documents) or state when not to use it, so it stops short of explicit routing.

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