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

Annotations already declare readOnly=true, idempotent=true, destructive=false, so the safety profile is covered. The description adds two genuinely useful traits beyond that: results are ranked via LLM re-ranking (implying non-deterministic ordering), and an auth requirement (registered handle + secret).

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?

Three short, front-loaded sentences with no filler; the core action leads, followed by mechanism and prerequisites. The '[stores]' prefix is the only wasted token.

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 search tool with no output schema, the description covers the action, mechanism, and auth, but says nothing about result shape, pagination, or what 'recall notes' vs 'memory entries' returns look like. Adequate for invocation, thin for interpreting results.

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 coverage is 50%: query and limit are documented in the schema, but handle and secret are not. The description partially compensates by flagging that a registered handle and secret are required, which clarifies the undocumented required handle parameter, though it adds nothing for `limit` semantics.

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 (search) and resources (recall notes AND memory entries), and the scope 'both' hints at something broader than a single memory store. However, it never distinguishes itself from the many near-identical siblings (memory_recall, search_memory, search_memory_facts), and the leading '[stores]' token is unexplained noise.

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?

Only a prerequisite is given ('Registered handle + secret required'). There is no guidance on when to use this versus memory_recall, search_memory, search_memory_facts, or list_memory, which is critical given the crowded memory-search sibling set.

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