learning_observe

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

Annotations establish it is not read-only but not destructive; the description adds the crucial boundary that it never changes Skills, Capabilities, GPT.md, or memory by itself. This prevents agents from assuming recording lessons has immediate side effects on knowledge artifacts, though it still doesn't say where the record is persisted.

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?

Two focused sentences with no filler: the action is front-loaded and the boundary condition is stated immediately after. Every sentence earns its place.

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 seven parameters, a nested lessons object, no output schema, and no per-parameter descriptions, the brief description leaves meaningful gaps: how lessons should be structured and scored, whether todo_id links to TODO tracking, and what happens after recording. It is not complete enough for an agent to use all fields confidently.

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 description gives semantic meaning to the core parameters: task, outcome, evidence ('evidence-backed'), and lessons ('learning candidates'), and the target enum values are reflected in the list 'Skills, Capabilities, GPT.md, or memory'. However, confidence, reuse_potential, summary, todo_id, and skills_used remain unexplained, and schema coverage is 0%, so the description only partially compensates.

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?

States a specific action (Record) on specific resources (evidence-backed task outcome and reusable learning candidates), and the second sentence scopes it as observation-only, distinguishing it from promotion tools like learning_promote. An agent can infer what this tool produces without opening the schema.

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?

The description implies the tool is for recording observations rather than applying changes, and 'by itself' hints that promotion is a separate step. However, it never names alternatives such as learning_promote or states when to choose this tool over learning_history or other learning-related tools.

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