Teach

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

Discloses that it stores a high-importance feedback memory that auto-surfaces in relevant tasks and can be listed/updated/deleted. No annotation contradictions; readOnlyHint=false and destructiveHint=false are consistent with a mutating but non-destructive store operation.

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?

Concise two-sentence description plus a third sentence on CRUD management. Front-loaded with the core verb and resource ('Teach the agent a durable behavior rule'). 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 8 parameters including a nested scope object, the description lacks coverage for most parameters. Output schema exists but is not referenced. The description explains the high-level behavior but not the configuration knobs, leaving agents underinformed.

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 adds minimal parameter information. Only 'instruction' and 'importance' are hinted; tags, nest, branch, scope, terse, and response_format are completely unexplained. The description should clarify these optional parameters for effective use.

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?

Clearly states 'teach a durable behavior rule' and distinguishes from sibling memory tools by emphasizing high-importance feedback that auto-surfaces in agent_prime. Examples like persistent preferences and coding standards further clarify purpose.

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 explicit use cases: 'set persistent preferences, coding standards, or workflow rules'. Implicitly differentiates from general memory tools by noting that teach memories can be managed via existing CRUD tools, though no explicit when-not-to-use is given.

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