Record Learning Reflection & Self-Improvement

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

Annotations already disclose the write profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description only needs to add context. It adds that records go into SQLite and persist across sessions, but does not address what happens on duplicate reflection submissions, whether entries are ever expired/overwritten, or auth requirements.

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?

A single front-loaded sentence with the verb first and no filler. It is dense with the recordable content types, though it could be split to surface usage guidance more prominently.

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?

For an 8-parameter, 5-required write tool with no output schema, the description identifies the main payload categories and the persistence target, which roughly matches the schema. It falls short on the two things the schema cannot convey: when this tool should be chosen over kilo_remember_fact and what a successful record produces.

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 88% schema description coverage, the schema already documents nearly every field (taskMode, taskSummary, correctApproach, lessonsLearned, skillsEvaluated). The description merely enumerates the same content categories and adds no format, syntax, or boundary guidance, so the baseline 3 applies.

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?

Specific verb 'Record' with a clear resource set (correct approaches, wrong paths/pitfalls, skill ratings, lessons learned) and a stated destination and motivation ('into SQLite to drive Kilo-Kit's continuous self-improvement across sessions'). An agent can tell what it does, but the description never distinguishes it from siblings like kilo_remember_fact or kilo_synthesize_skill, which also persist learning artifacts.

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?

Usage is only implied by the framing: 'across sessions' and 'continuous self-improvement' suggest calling it after completing a task. There is no explicit when-to-use trigger, no when-not, and critically no routing away from kilo_remember_fact, which appears to overlap in storing durable knowledge.

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