memory_search

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It only mentions 'active (or stale)' when referring to memories, but does not disclose whether the operation is read-only, what results are returned (sorting, pagination), or any side effects. It also omits permission requirements. The worktree behavior ('silently ignored') is described in the schema, not the description, so it doesn't count here. This leaves significant gaps.

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 a single, well-formed sentence that is immediately clear and front-loaded with the core action. There is zero redundancy or filler. Every word contributes to meaning, making it highly efficient.

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 three parameters, no output schema, and no annotations, the description is far too brief. It does not explain the result format, ordering, what constitutes 'memories', or how to interpret 'active' vs 'stale'. It also lacks integration of the worktree parameter's behavior, which is only in the schema. The tool would require the agent to make many assumptions, making it incomplete for a production context.

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 33% (only worktree has a description). The description adds minimal value: it implies that 'query' is the keyword for search, but provides no additional context for 'limit' or 'worktree' beyond what the schema already offers. The description does not clarify defaults, formats, or edges cases, failing to compensate for the low schema coverage.

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 the verb 'search' and the resource 'repo memories' with a qualifier 'full-text' and 'by keyword', distinguishing it from semantic_search and symbol-specific lookups. It also notes the 'active (or stale)' scope, which adds specificity. This is a strong, specific purpose statement.

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 implies usage for keyword-based full-text search but provides no explicit guidance on when to use this tool over alternatives like semantic_search or memory_for_symbol. There is no mention of exclusions, prerequisites, or alternative tools, leaving the decision to the agent's inference from sibling names. This is minimal implicit guidance, not explicit.

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