Ask memory

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 adds useful context: the prioritization of approved conclusions and the return format including provenance and recallId. However, it does not disclose read-only nature, permissions, rate limits, or any side effects, leaving gaps for a query tool without annotation support.

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 concise sentence that front-loads the core purpose and return values. It is efficiently worded with no filler, though it could benefit from a structured breakdown of parameters and usage 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?

Given 5 parameters, no annotations, and no output schema, the description is far from complete. It omits parameter semantics, usage alternatives, error conditions, and any safety or permission context. An agent would be under-equipped to invoke this tool correctly without opening the schema and guessing at parameter meaning.

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?

Schema description coverage is 0%, so the description must compensate for parameter meaning. It fails to explain any of the 5 parameters: 'kind', 'tags', 'limit', 'namespace', and even 'question' is only implied by the tool name. The phrase 'scoped or explicitly requested raw evidence' hints at scoping but does not map to specific parameters like tags or namespace. This is a critical gap.

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 asks memory, specifying an order ('approved conclusions first, then scoped or explicitly requested raw evidence') and the return fields ('answer, exact provenance, recallId'). It is a specific verb+resource, but does not explicitly differentiate from sibling tools like search_memory or recall_memory, so it lacks sibling distinction.

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 implies this is the primary ask tool but provides no explicit guidance on when to use it versus alternatives like search_memory or recall_memory. It mentions an ordering of retrieval but not when this tool is preferred over others, and no exclusions or alternative conditions.

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