Record a canonical learning

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

The description goes far beyond the idempotentHint annotation by explaining the REPLACES behavior, 'no appended contradictions', git history preservation, and frontmatter provenance accumulation. It fully discloses side effects and the canonical-replacement model.

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 dense and front-loaded with purpose and an example. Every sentence earns its place, covering purpose, behavior, exclusions, and downstream effects in a single well-structured paragraph.

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?

The description covers purpose, exact file path (kb/learning-<slug>.md), replacement semantics, versioning, provenance, and indexing. Although there is no output schema, the return behavior is not critical for a write-oriented tool; the description gives the agent everything needed to select and invoke it.

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?

The input schema already describes topic, ticket, and content (75% coverage). The description adds meaningful semantics: topic as canonical key for updates, content as current complete truth that replaces wholesale, and ticket as provenance. The project parameter is not described in either, but it is self-explanatory.

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 opens with a specific verb and resource: 'Record a durable, re-usable truth discovered while working' and names concrete examples (API gotcha, invariant, constraint). It explicitly distinguishes itself from sibling tools by saying 'not work narration (that's log_work) and not in-flight research (that's append_research)'.

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?

It provides explicit when-to-use guidance ('knowledge the NEXT ticket needs') and explicitly names alternatives with their purposes. It also explains that learnings are indexed and auto-injected into work packets, giving the agent clear selection criteria.

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