get_learnings

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

With no annotations, the description carries the burden and does well: it declares read-only/advisory status, that it does not substitute for base rules or the verifier, and the graceful empty-result behavior ('si no hay nada util, lo dice y no pasa nada'). It does not explain scope/permanence of the stored memory (how it is accumulated or whether results are cached), leaving a small 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?

Front-loaded with what is returned, then the read-only/advisory constraint, then the call ordering. Slightly dense with parenthetical enumerations, but every sentence contributes distinct guidance.

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?

No output schema exists, and the description compensates by naming the three categories of returned content and the empty case. Combined with the sequencing guidance, an agent has enough to call it correctly; only memory-scope details are missing.

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?

Single parameter with 100% schema description coverage, so the baseline is 4. The description adds no extra meaning about projectRoot beyond the schema, which is acceptable at this coverage level.

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 verb and resource: returns what the MCP remembers about THIS repo from prior uses, enumerated as conventions, one-off user decisions, and recurring verifier errors. It explicitly distinguishes itself from the sibling get_rules and from the verifier, so an agent can route correctly 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?

Gives explicit sequencing ('Llamala justo despues de get_rules') and states the intended downstream action (use the data to PROPOSE defaults that the user confirms). It also names the alternative, get_rules, and clarifies that this tool does not replace or relax it.

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