Recall

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

Without annotations, the description carries the burden of disclosing behavior, and it does so well by explaining how score_threshold applies to semantic cosine and episodic decay scores, and how category only affects lessons. It stops short of explicitly stating side-effect-free behavior, but 'Search' and the parameter semantics strongly imply a read-only 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-organized: a one-sentence summary followed by a tight, informative arg list. Every line adds value, and defaults are included inline, making it easy to scan without unnecessary prose.

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 technical complexity of the tool and the complete lack of schema-level descriptions or annotations, the description covers all essential aspects: query semantics, filtering modes, threshold behavior, and conditional category logic. Since an output schema exists, omitting return-value details is acceptable and does not detract from completeness.

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 no descriptions, so the description fully compensates by explaining every parameter, including valid memory_type values, defaults, threshold semantics, and conditional category filtering. This is exemplary semantic enrichment beyond the raw input schema.

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 opens with 'Search memory by semantic similarity,' a specific verb + resource that clearly defines the tool's function. This distinguishes Recall from sibling write/delate tools like Remember, Forget, and PruneMemory, and from MemoryStats.

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 clearly implies when to use Recall—when retrieving semantically related memory content—but it does not explicitly compare it to alternatives or state when not to use it. The sibling tool names provide context, but the description itself offers no direct routing guidance.

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