memory_search

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

With no annotations, the description carries the full burden, and it discloses real behavioral specifics: local TF-IDF cosine similarity, recency and importance boosts, and that it searches rather than mutates. It does not describe return format or edge cases, but the search behavior itself is unusually well specified.

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 sentence that front-loads the action and resource, then packs in the algorithm and ranking factors without wasted words. Every phrase earns its place.

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 two-parameter search tool with a complete schema, the description covers the core behavior and ranking logic well. The only notable absence is the output shape, since there is no output schema to fill that gap, but an agent can reasonably infer that matching memories are returned.

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 schema already documents both parameters at 100% coverage, so the baseline is 3. The description adds meaning by clarifying that 'query' should be a semantic/free-form expression and that result ordering is influenced by recency and importance, which the schema does not state.

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 names a specific action ('Semantic search') and a clear resource ('stored memories'), and the algorithmic qualifiers make the tool distinct from sibling memory-management tools such as memory_add or memory_clear. An agent can tell this is the retrieval/query tool at a glance.

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?

It clearly implies when to use it: whenever the agent needs to retrieve previously stored memories semantically. It does not explicitly name alternatives or exclusions, so it stops short of a 5, but the context is strong enough that the agent would not reach for memory_add or memory_forget.

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