core_set

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

Discloses key behaviors: always shown in brief, sorted by priority descending, priority range 0-100, content capped at 1KB. With no annotations provided, the description fully covers safety and operational traits.

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?

Extremely concise: two short paragraphs with no wasted words. Front-loaded with purpose, then usage guidelines, then parameter details. 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?

Covers purpose, usage, parameters, behavioral traits, and constraints. Output schema exists, so return values need no explanation. Complete for a 3-parameter upsert 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?

Adds meaning beyond the input schema: explains priority range and default sorting behavior, content size limit, and the semantics of 'upsert'. Schema coverage is 0%, but description compensates thoroughly.

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 explicitly states 'Upsert a core-memory entry', using a specific verb and resource. It distinguishes from sibling tools like core_get, core_list, core_remove by focusing on the write operation and memory surface.

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?

Provides clear when-to-use and when-not-to-use guidance ('Use sparingly', 'not a note store') with concrete examples (good vs bad usage), helping the agent avoid misuse.

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