search_memory

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

With no annotations provided, the description carries the full behavioral burden. It discloses that all space-separated words must appear, that quotes and operators are treated as plain text (not FTS), and that it works with CJK substrings. It also mentions the llm parameter is for the usage audit log, adding operational context. It does not discuss result format or potential side effects, but for a read-only search this is sufficient.

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 efficient and well-structured: a two-sentence behavioral summary followed by a compact parameter list. It front-loads the key matching semantics and then documents each parameter without redundancy. It is slightly longer than strictly necessary but 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?

Given the tool has an output schema (not shown but present), the description need not explain return values. It covers the search behavior, language support, syntax limitations, and all parameter semantics. An agent has everything needed to call the tool correctly, including the audit log requirement for llm.

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 0%, meaning the schema provides no field-level guidance. The description compensates fully by explaining each parameter in the bulleted list: query, project, type, limit, and llm. It adds concrete semantics (e.g., 'restrict to one project', 'max results', 'your name for the usage audit log') that the schema alone does not convey.

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 opens with a clear, specific verb-resource statement: 'Keyword search over titles, content and tags.' It explicitly distinguishes itself from semantic search by noting it is not FTS syntax and that every word must appear, which differentiates it from the sibling search_memory_semantic without needing to inspect the sibling.

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 explains when to use this tool by defining its exact matching behavior and noting it handles CJK substrings. It does not explicitly name alternative tools or state when NOT to use it (e.g., for fuzzy/meaning-based search), but the contrast with semantic search is implied. The behavior is clear enough for an agent to infer the appropriate context.

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