add_learning

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that the tool 'Adds' something, implying a write operation, but it does not disclose whether entries are append-only, deduplicated, persisted for later retrieval, or what kind of response is returned. For a mutation tool, this is a meaningful gap.

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 a single, front-loaded sentence that states the action, object, and context without any redundant phrasing. It is appropriately sized for a simple mutation tool whose parameters are fully self-documented in the schema.

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 schema fully describes the parameters, so the invocation details are mostly covered. However, the description does not mention where the learning is stored, whether it can be retrieved later, or how it relates to sibling tools like get_learnings, leaving some context incomplete for an agent deciding whether and how to call 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?

Schema description coverage is 100%, so the input schema already documents all five parameters, including examples for topic and the 0-1 range for confidence. The description adds no parameter-specific meaning beyond the schema, so the baseline score of 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?

The description uses a specific verb ('Add') and a specific resource ('learning or insight gained during analysis'), making the tool's purpose clear. It distinguishes from search tools and even from log_decision by framing this as capturing analysis-derived knowledge, though it does not explicitly name sibling alternatives.

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?

'Gained during analysis' provides a clear contextual trigger for when to use this tool: when the agent has produced a learning or insight while analyzing. It does not explicitly describe exclusions or alternatives, but the purpose of adding knowledge is well-enough scoped.

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