memory_world_set

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

No annotations are provided, so the description fully carries the behavioral disclosure burden. It reveals important traits: URL scheme validation ('any other scheme is rejected'), freshness_class setting trust decay at read time, supersession behavior ('A newer source supersedes an older value at the same slot'), and the returned action set. It could go further on edge cases like missing source_url or auth, but it is notably transparent.

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 well-structured: purpose first, then usage guidance, then a compact Args list, and finally the return shape. Every sentence adds substantive value without redundancy, and the format is front-loaded with the most important information.

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 tool with 9 parameters and no annotations, the description is quite complete. It covers the tool's purpose, routing, parameter semantics, and return values (also aided by an output schema). Key behaviors like supersession and trust decay are explained. The main gaps are explicit definitions for required parameters and the optionality of citation fields, but overall it provides a strong operational picture.

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?

With 0% schema description coverage, the description's Args section is critical. It explains source_url's http(s) requirement, source_quote length, freshness_class enum meanings, confidence bounds, and the optional retrieved_at/content_hash pair. However, it does not explicitly describe the required parameters entity, attribute, and value, leaving them to inference from the schema titles.

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 it asserts a canonical WORLD fact sourced from external knowledge, with examples (versions, prices, who-holds-a-role, research findings). It explicitly distinguishes this from user/project facts, which differentiates it from sibling tools like memory_fact_set. The verb 'Assert' plus 'WORLD fact' is specific and action-oriented.

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 gives clear context for when to use this tool: 'Route verified web/docs findings here' and 'kept separate from user/project facts.' This implies the alternative use of user/project fact tools, though it does not name a specific sibling. It also notes that a newer source supersedes an older value, which is a key usage rule.

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