expand_memory

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

With no annotations provided, the description carries the full burden. It discloses key behaviors: returns COMPLETE content, accepts up to 10 ids, and ids derive from get_context/recall. However, it does not disclose potential side effects, error handling, or whether any permissions are required. The read-only nature is implied but not stated explicitly.

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 two sentences, front-loaded with the purpose, and the Args section is compact and directly informative. No redundant words or restatement of schema details.

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 simplicity (one parameter, no enums, has output schema), the description is largely complete: it specifies the ID source, maximum count, and purpose. It omits error behavior and does not explicitly state that get_context/recall must be called first, but the reference to their #id pointers implies that prerequisite.

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 provides only the type and array structure for 'ids', with no description. The text compensates by explaining the ids are pointers from get_context/recall and limited to max 10, adding meaningful context beyond the raw schema. This is sufficient for correct invocation.

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 function: 'Drill-down dal contesto compatto: il contenuto COMPLETO di una o più memorie.' It uses a specific verb ('drill-down'), names the resource ('memories'), and distinguishes from siblings by emphasizing it returns complete content from compact context, unlike recall/get_context which provide compact summaries.

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 clear usage context by specifying the IDs come from '#id pointers of get_context/recall', indicating when to use it. However, it does not explicitly state when NOT to use this tool versus alternatives like get_memory or recall_associative, lacking explicit exclusions.

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