search_memories

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

With no annotations, the description carries the full burden of behavioral disclosure. It adds valuable non-obvious context: image memories may include temporary image_urls that expire after a few hours, and the search is hybrid (semantic + keyword) with ranking by relevance. This goes beyond the bare operation and helps the agent understand potential pitfalls.

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 concise and well-structured. It front-loads the primary purpose, then adds the image URL caveat, and finally provides context and usage guidance. Each of the three short paragraphs serves a distinct purpose without redundancy or excessive detail.

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 having no output schema or annotations, the description covers the essential aspects: what it searches, how results are ranked, the presence of expiring image URLs, and when to use it. It could be more complete by describing the returned memory structure or mentioning default bucket behavior, but it is sufficient for a search operation with well-documented parameters.

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 covers 100% of parameters with descriptions (query, limit, bucketId). The tool description does not introduce additional parameter-level meaning, such as accepted formats or constraints. Thus, the baseline of 3 applies; the description doesn't go beyond the schema's already adequate documentation.

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 clearly states what the tool does: 'Search the user's saved memories using hybrid semantic + keyword search.' It includes a specific verb (search), a specific resource (saved memories), and a result description (ranked by relevance). It is distinct from sibling tools like search_uploaded_files, which targets files, and store_memory, which is for saving.

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 provides a clear usage context: 'Use when looking for specific saved information.' This gives the agent a clear trigger for selecting this tool. However, it does not explicitly name alternatives or exclusions, such as noting that search_uploaded_files should be used for file content, so it doesn't fully differentiate between siblings.

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