Metis — Discovery Intro

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

With no annotations, the description fully discloses behavior: it returns 3-5 capabilities, is a no-op (returns empty string) if already given or tips are off, and implies idempotency. No contradictions.

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?

Three sentences, each essential. Front-loaded with main purpose, then usage rules, then edge conditions. No wasted words.

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 no parameters and an output schema, the description explains the output (3-5 capabilities, empty string in some cases) and references the sibling tool. Fully adequate for a simple 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?

No parameters exist, so schema coverage is 100%. The description adds value by explaining the return behavior and conditions for empty string, which goes 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?

The description clearly states it returns 'the 3-5 highest-value capabilities' for a first-run orientation, and distinguishes itself from sibling 'next_discovery_tip' by specifying that after this intro, that tool should be used.

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?

Explicitly defines when to use: 'Use ONCE for a brand-new user (or when they ask what can you do?)' and specifies post-use behavior: 'After this, rely on next_discovery_tip for the long tail.' Also notes no-op conditions.

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