Metis — Next Discovery Tip

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

No annotations provided, so description carries full burden. It discloses rate limiting (≤1 tip/20 min, ≤3/day), respects user settings (off/snooze/power-user), records to avoid repeats, and returns empty string when nothing to show. Does not mention side effects but operation is read-like and non-destructive.

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?

Description is about 120 words, front-loads purpose, and every sentence adds value. Minor redundancy in emphasizing 'earned discovery' but overall efficient and well-structured.

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 tool's simplicity (1 optional param, no required, output schema exists), the description covers behavior, return values, when to call, and constraints. No additional information needed; output schema handles return value details.

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 has one optional parameter 'context' with no description in schema (0% coverage). Description explains it as 'comma-separated trigger tags describing what the user is doing', adding essential meaning beyond the 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?

Description clearly states that it returns one earned, not-yet-shown feature tip or empty string. Verb 'return' and resource 'feature tip' are specific. No sibling tools with similar purpose exist, so it is well-distinguished.

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?

Description lists explicit natural trigger moments (e.g., user starts a project, writes R code) and instructs to pass context as comma-separated tags. Does not explicitly state when not to use, but the context implies limited applicability. No alternative tool is mentioned, but no sibling tool serves a similar function.

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