save_learning

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

With no annotations, the description carries full burden. It discloses that learnings persist forever, are updated in place on duplicates, and auto-surface in search_context. This covers key behaviors beyond the basic create operation, though it could mention deletability (inferred from sibling delete_learning) and immediate effects.

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 three sentences with no extraneous content. The first sentence states the core purpose, the second contrasts with sessions, and the third covers duplicate handling. Every sentence is essential and the information is front-loaded.

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 save operation with no output schema, the description covers the essential aspects: what is saved, permanence, duplicate behavior, and integration with search_context. It could mention category enum or that learnings are immediately available, but these are either in the schema or implied. Overall, it is sufficiently complete.

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 baseline is 3. The description adds value by revealing that the combination of 'category' and 'rule text' determines duplicate detection and triggers update-in-place behavior. It also clarifies project is optional with an example, going beyond the schema's 'description' field.

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 clearly states the tool saves a permanent operational rule learned during a coding session, distinguishing it from sessions which are ephemeral. The verb 'save' and resource 'permanent rule' are specific, and the contrast with sibling 'save_session' makes the purpose unambiguous.

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 contrasts with sessions ('Unlike sessions (ephemeral'), guiding when to use this tool over save_session. It also explains that learnings auto-surface in search_context, indicating their use for AI agents. While not exhaustive, it provides clear context for appropriate usage.

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