list_learnings

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

With no annotations, the description carries the behavioral disclosure burden. It adds meaningful context: learnings are 'permanent', contain 'operational rules that have been discovered across sessions', and are automatically indexed in search results. It does not explicitly state read-only safety or return behavior, but 'List' combined with the permanence and search-integration notes is sufficient context for a simple read tool.

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 two efficient sentences with no filler. It front-loads the main action, clarifies the resource nature, and then provides the sibling-tool routing, all in minimal space.

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 a simple, optional-parameter list tool, the description covers the core semantics, the alternative keyword-search path, and the distinctive permanence/indexing behavior. The `since` parameter is left entirely to the schema, but the schema covers it thoroughly, and there is no output schema to explain. Minor gaps such as ordering or pagination are not critical for this tool.

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 schema already documents both optional parameters in detail, including the 'since' boundary semantics and category examples. The description adds only the category-filter concept, which is already present in the schema, so the baseline 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 opens with a specific verb and resource: 'List all permanent learnings, optionally filtered by category.' It clearly distinguishes this tool from sibling search_context, which is routed to for keyword-based lookup.

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 explicitly tells the agent when to use search_context instead ('Use search_context to find learnings by keyword'), and explains that learnings are automatically included in search results. This gives a clear decision rule between two overlapping tools.

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