recall

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

With no annotations, the description fully discloses key behaviors: it is read-only ('Read-only; scoped to what you can read'), lexical-match based, ranks human-stated facts highest, and notes it is a 'Hosted API only.' This is comprehensive and leaves no ambiguity about safety or scope.

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, dense paragraph of about five sentences, each adding meaningful information. It front-loads the core purpose, then adds result details, usage guidance, and limitations—no fluff or repetition.

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?

Despite lacking an output schema, the description explains the return format. All six parameters are covered by the schema, and the description provides sufficient behavioral and usage context for a search tool. No gaps remain for agent decision-making.

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 input schema has 100% description coverage, so the description adds value by explaining the overall result structure ('key, value, source, and the task they live on ranked by relevance') and use context. This goes beyond the schema's individual parameter descriptions.

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 specifies a clear verb ('search') and resource ('decision-memory across ALL tasks'), explicitly distinguishing it from sibling tool 'get_task_context' which is task-specific. The phrase 'without knowing which task recorded it' highlights its unique cross-task scope.

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 explicitly advises using the tool 'at the START of new work to avoid re-deciding something already settled.' It also notes the lexical matching limitation ('exact-ish terms beat paraphrases'), providing clear context, though it does not directly name alternatives or situations to avoid.

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