Search memory

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds useful behavioral context about response-size capping and the full_content tradeoff, plus the hybrid retrieval mode, though the capping detail largely restates the full_content schema description.

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?

Purpose and retrieval method are front-loaded, followed by usage guidance and exclusions. The long list of trigger phrases is effective but somewhat verbose, though each clause serves the routing purpose.

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?

For a five-parameter read tool with no output schema and covered annotations, the description gives enough routing and behavioral context to call it correctly. Minor gaps remain around as_of semantics and include_card, but those are fully documented in the schema.

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 80%, so the schema already documents as_of, max_results, full_content, and include_card. The description only reinforces full_content usage ('pass full_content=true only when the full matching row is required') and does not explain as_of or max_results, so it adds marginal value beyond the schema baseline.

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?

States a specific verb and resource ('Searches the user's stored facts and session history') plus the retrieval method ('hybrid semantic + keyword retrieval'). It also differentiates from the sibling load_memory by instructing not to trigger when load_memory was just called.

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?

Provides explicit trigger conditions (a long list of user phrasings and contexts), rules for implicit triggers ('Trigger even when the user doesn't explicitly say search'), and explicit non-triggers (one-shot math, translations, definitions, no plausible stored context, or immediately after load_memory). This is close to exhaustive routing guidance.

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