memory_digest

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

With no annotations, the description carries full burden for behavioral disclosure. It thoroughly describes the tool's behavior: deterministic, combines hybrid-search hits, supersession lineage, related memory ids, and TODO/issue matches. It also notes always returning raw source ids. However, it does not explicitly state read-only nature or auth requirements, but the description is adequate for a read operation.

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 well-structured with a summary paragraph followed by a parameter list. It is front-loaded with the core purpose. Although slightly verbose, every sentence adds value, and the format aids readability.

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 complexity (14 parameters, no annotations, but has output schema), the description covers all key aspects: what the digest includes, parameter behaviors, and the guarantee of returning raw source ids. The presence of an output schema means return value details are not required, but the description still provides useful context about the output composition.

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 description provides a detailed Args section explaining each parameter's purpose and default values (e.g., topic: 'Subject to digest', k: 'Maximum active search hits and TODO/issue matches'). Since schema description coverage is 0%, the description adds essential meaning beyond the schema's basic type and name, fully compensating for the 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 returns a deterministic digest of memories related to a topic. It specifies the verb ('return') and resource ('memories digest'), distinguishes from narrative generation, and differentiates from sibling tools like memory_hybrid_search or memory_get by focusing on aggregation.

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 context for when to use the tool ('agents that need current context') and includes guidance that raw source ids are returned for inspecting primitives if the digest is too broad or narrow. However, it lacks explicit alternatives or when-not-to-use scenarios, which would improve clarity given the many sibling tools.

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