search_memories

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

With no annotations, the description still discloses key traits: it is a read operation ('READ'), results are capped and never a full dump, and 'Candidates are never returned' clarifies result semantics. Missing are ranking behavior details, whether results span across projects in a defined order, or any auth/permission notes.

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?

Three tight sentences with the operation type front-loaded ('READ'), then scope, then result bounds. The parenthetical 'or `project`, a label or id' is slightly awkward but earns its place by defining the parameter.

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?

An output schema exists, so return-value explanation is unnecessary, and the description covers scope, bounded results, and exclusion of candidates. What remains thin is guidance on choosing this tool over list_recent and details on cross-project result ordering, but nothing required to invoke it correctly is missing.

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 coverage is 0%, so the description must compensate, and it does reasonably: `query` is implied as the search input, `limit` caps the hit count, and `project` is clarified as 'a label or id' including global/linked scope. It does not state the default limit (8) or the query syntax, keeping it short of a 5.

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?

States a specific verb (relevance-ranked search) and resource (long-term memories), plus the scope: current project, linked projects, and global memories, with optional override by `project`. It is clearly distinguishable from siblings like list_recent, store_memory, and forget_memory without opening any schema.

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 framing 'Returns at most `limit` hits, never a full dump' implies this is the targeted-search path rather than enumeration, which is useful context. However, no sibling is named and there is no explicit when-to-use/when-not guidance versus tools like list_recent or memory_status, so the agent must infer the choice.

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