Metis — Query Research Timeline

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

Without annotations, the description carries full burden. It covers filtering behavior and defaults but does not explicitly state that the tool is non-destructive or read-only. The behavioral traits are mostly clear, but some aspects (like side effects) are implied rather than stated.

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: a concise one-sentence summary, followed by a brief behavioral paragraph, then parameter documentation. No unnecessary words; every sentence adds value.

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 output schema exists (returns not needed), the description covers purpose, parameters, and behavior completely. It explains the superseded concept and filtering options, leaving no obvious gaps for an agent to select and invoke the tool.

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 coverage is 0%, so the description must compensate. It provides clear, detailed semantics for all three parameters: entity (partial match), since_date (ISO format), show_superseded (boolean, defaults to False). This adds significant value beyond the bare schema.

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The description uses specific verb 'query' and resource 'research beliefs', highlighting temporal evolution and superseded claims. It clearly distinguishes this tool from siblings like search_memory or get_research_context by focusing on chronological ordering and belief history.

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 explains default behavior (superseded hidden) and when to show them (to trace reasoning). It implies context for usage but does not explicitly state when to prefer alternatives. Good but could be more thorough.

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