memory_world_search

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

Annotations already declare readOnly/destructive/idempotent hints, so the bar is lower, and the description adds genuinely useful semantics: age-decayed effective_confidence, a stale flag with an explicit re-verify instruction, and source_url/source_quote for citation. It stops short of describing ranking or latency behavior, but the field-level disclosure is substantive.

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-loads purpose, then the trigger condition, then entry semantics, then the return shape. Every sentence carries distinct information with no restatement of the name or schema.

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?

With an output schema present and 100% parameter coverage, the description need not explain return format, so its job is mostly done. It covers trust signals (confidence, stale, citation) well; the only real omission is how it relates to memory_world_set for writes and other retrieval siblings.

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%, so the schema already documents query, top_k, and verbose; baseline 3 applies. The description adds no parameter-level guidance (no hints on query phrasing, sensible top_k, or when verbose pays off), so it neither helps nor compensates here.

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 (Search) and a scoped resource (current WORLD facts / sourced external knowledge) and explicitly distinguishes itself from generic memory recall by naming the domain. An agent can tell this apart from memory_search, memory_fact_get, or document_search without opening any schema.

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 concrete activation condition: 'Use when a task turns on an external fact your training data may be stale.' That is a real when-to-use rule, but it names no alternative tools (e.g. document_search or memory_search) and gives no when-not boundary.

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