map_learned

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

With no annotations, the description does carry some behavioral weight: 'Already applied locally' signals these are settled, non-pending entries, and it explains the meaning of a returned field ('shared'). It does not state permissions, ordering, size, or any mutation behavior, though the wording implies a read-only retrieval.

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 compact sentences with no filler, and the core subject is front-loaded. Minor deduction because the opening is a bare noun phrase rather than a statement of what the call does.

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 zero-input tool with no output schema, the description should at least characterize the returned collection (fields beyond 'shared', ordering, volume). It covers the resource and one field, which is the minimum viable level, but leaves the agent guessing at the response shape.

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 tool takes zero parameters and the schema is an empty object, so there is nothing for the description to disambiguate. Baseline 4 applies for a no-parameter tool.

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 identifies the resource concretely (button-map fixes and lessons learned from local use), which differentiates it from siblings like lesson_record and memory_recall, but it never states the action — no verb like 'returns' or 'lists'. An agent can guess this is a read of accumulated fixes, but must infer it.

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?

There is no explicit when-to-use guidance, no exclusion criteria, and no named alternative among the many sibling tools (lesson_record, memory_recall, share_preview). The clause about 'shared' hints at a review-queue relationship but does not tell the agent when to pick this over those siblings.

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