Consolidate Memories

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it's a mutation tool (implied by 'merge'), offers a safe preview mode, uses similarity clustering, and preserves facts during merging. However, it lacks details on permissions, rate limits, or error handling, which would be helpful for a tool that modifies data.

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 front-loaded with the core purpose, followed by usage details and an example, all in three concise sentences. Every sentence earns its place by adding critical information (mechanism, action differentiation, example), with no wasted words or redundancy.

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 tool's complexity (merging based on similarity with mutation potential) and lack of annotations or output schema, the description is mostly complete: it covers purpose, usage, parameters, and behavior. However, it could improve by mentioning output format for previews or error cases, which would help an agent handle results better.

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 schema description coverage is 100%, so the baseline is 3. The description adds value by explaining the semantics of the 'action' parameter ('preview = dry run showing candidates, execute = actually merge') and providing context for 'threshold' ('Lower = more aggressive merging'), which clarifies usage beyond the schema's enum and numeric range. It doesn't detail default values or thresholds extensively, but enhances understanding.

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's purpose with specific verbs ('find and merge similar observations') and resources ('observations', 'consolidated records'), distinguishing it from siblings like memorix_deduplicate (likely for exact duplicates) or memorix_search (for retrieval). It explains the mechanism ('text similarity to cluster related observations by entity+type') and outcome ('reduce memory bloat'), making the function 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 provides explicit usage guidance: it specifies when to use action='preview' ('to see candidates without changing data') versus action='execute' ('to merge'), and includes an example scenario ('10 similar gotchas about Windows paths → 1 consolidated gotcha'). It also implies when not to use it (e.g., for exact duplicates, which might be handled by memorix_deduplicate), though alternatives aren't named directly.

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