memory_recall

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

Even though no annotations are provided, the description discloses important behavior: context is soft by default, strict_context=true isolates the query, include_neighbors hydrates graph neighbors, neighbor_limit bounds hydrations, and metadata reports when more neighbors were available. It does not explicitly state read-only behavior or broader response shape, but it covers the core operational traits clearly.

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 compact, front-loaded with the core purpose, and every sentence adds a distinct operational fact. It avoids restating the schema and packs useful behavioral detail into a short, scannable paragraph.

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?

The description covers most invocation-critical behavior and even mentions metadata availability. However, the agent has no output schema to lean on, and depth and token_budget remain unexplained. The phrase 'Search memories by text, context, activation, and confidence' also introduces activation and confidence without mapping them to schema parameters, leaving some ambiguity in how to leverage those signals.

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 provide meaning for parameters. It does so for context, strict_context, include_neighbors, neighbor_limit, limit, and edge_types, even giving an example edge type 'RESPONDS_TO'. However, depth and token_budget are present in the schema but left unexplained, so the compensation is not complete.

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 a specific verb-resource pairing: 'Search memories by text, context, activation, and confidence.' It clearly distinguishes this tool from sibling memory_context by saying, 'Use memory_context to assemble working context.' An agent can reliably identify memory_recall as the targeted-memory-search tool.

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?

'Use this for a targeted question. Use memory_context to assemble working context' explicitly tells the agent when memory_recall is appropriate and when the sibling is better. It also explains when to set strict_context, include_neighbors, and edge_types, so selection and invocation conditions are directly actionable.

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