memory_search

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

With no annotations, the description carries the full burden. It usefully discloses the retrieval strategy (hybrid keyword + local semantic) and that the corpus is shared rather than private, which helps the agent reason about recall quality and privacy. It says nothing about result limits, pagination, latency, or whether the call itself writes anything.

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?

A single well-formed sentence with the mechanism and timing front-loaded and zero filler. It is arguably undersized for a nine-parameter tool, but nothing in it is wasted or buried.

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 nine-parameter retrieval tool with no annotations, no output schema, and near-zero schema documentation, the description should carry much more of the load. It never explains the scope/level/status filter dimensions or result sizing, so an agent cannot call it correctly without experimentation.

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 only 11% across 9 parameters, so the description is expected to compensate and largely does not. It conveys nothing about top, scope, memory_level, memory_status, injection_mode, or context_budget_chars, leaving the agent to guess at filter and budget semantics from bare enum names.

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 gives a specific verb ('Search') plus resource ('the user's shared SecondBrain') and even names the retrieval mechanism ('hybrid keyword and local semantic retrieval'). That is enough to distinguish it from read-by-id siblings like memory_get or memory_related, though it never explicitly contrasts itself with them.

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?

'before substantive tasks' gives one implied condition for calling it, which is more than nothing. However, no alternatives are named (e.g., memory_recent for time-based recall, memory_get for a known id) and no exclusions are stated, so the agent must infer when this is the right entry point.

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