agent_recall

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

Discloses read-only nature and describes return formats for both with and without key, including error cases. No annotations provided, so description carries full burden; adequately transparent but could add more about idempotency or side effects.

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?

Concise, front-loaded with core action, no unnecessary words. Every sentence adds value.

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?

Complete for a read-only tool with one optional parameter. Covers usage, alternatives, return formats, and edge cases (empty memory, not-found). No output schema, so description adequately explains returns.

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?

Single parameter 'key' with clear description that explains behavior when omitted (list keys) and when provided (read value). Schema coverage is 100%, and description adds value beyond 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?

Clearly states it reads a value or lists keys from encrypted agent memory. Distinguishes from siblings by referencing get_project_context and get_secret.

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?

Explicitly advises when to use (start of agent loop, rehydration, single fact lookup) and when to prefer alternatives like get_project_context and get_secret.

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