memory.reconcile

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

With no annotations provided, the description carries full burden. It says it 'removes orphaned vectors,' which implies destructive action, but it doesn't disclose whether this action is reversible, what side effects occur (e.g., broken links), or whether it requires special permissions. The term 'remove' is clear but the behavioral profile around safety and rollback is opaque.

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, short sentence in Portuguese. It is concise and front-loaded with the main action. However, it could add more value without bloat by clarifying the project parameter or usage context. No wasted words.

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?

Given the destructive behavior (removal of vectors), the lack of annotations, and incomplete parameter documentation, the description is insufficient for safe use. An agent cannot tell whether running this tool is safe, what data will be removed, how to limit scope (project parameter), or what to expect after. For a tool acting on two databases, much more context is needed.

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 input schema has one optional parameter (project) with no description and 0% schema coverage, meaning neither schema nor description explains what project does. The description does not clarify whether project limits reconciliation to a specific project or what leaving it null mean. Baseline is 4 for 0 params but since there is 1 param with no context, a 3 is appropriate—the param semantics are incomplete.

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 states it verifies consistency between Neo4j and Qdrant and removes orphaned vectors. This tells the agent the action (verificar/remover) and the resources (Neo4j, Qdrant, vetores órfãos), but it doesn't specify what concrete outcome occurs (e.g., which tool is authoritative, what data is affected). Given the large sibling set, it distinguishes from pure query or mutation tools like memory.get or memory.upsert, but it's somewhat vague on the exact scope of 'consistência'.

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?

No guidance on when to use this tool versus siblings like memory.consolidate, memory.find_duplicates, or memory.reflect. All four deal with data health. The description does not tell the agent whether this is a maintenance task to run regularly, or only after certain operations. Also no mention of prerequisites or when not to use it.

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