memory.search

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

No annotations exist, so the description carries the full burden. It does disclose two behavioral traits: results are 'concise' and it does not load full documents, signaling a lightweight, non-destructive search. But it leaves the meaning of 'candidate' ambiguous (possibly the MemoryStatus enum value) and does not disclose default filtering or sort behavior.

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 front-loaded sentence with no waste; 'Find' leads with the action. It is efficient with the content it has. However, it is so terse that it borders on under-specification for a 16-parameter tool.

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?

A 16-parameter search tool with no annotations, no parameter descriptions, and no usage guidance leaves invocation semantics largely to guesswork. The output schema covers return values, which is good, but an agent cannot know how filters compose, what relation_depth means, or what 'secondary-context' selects. The description is insufficient for reliable tool invocation.

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% — all 16 parameters are undocumented — and the description mentions no parameters at all. Parameter names give some hints (limit, exact, user_id), but opaque parameters like relation_depth, minimum_importance, and memory_types go unexplained. With zero coverage and zero description compensation, this is a critical gap.

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 uses a specific verb ('Find'), a resource type ('secondary-context candidates'), and a distinguishing constraint ('without loading full documents'). This separates it from memory.read, which presumably loads full documents. However, 'secondary-context' is domain jargon that is never defined, slightly weakening clarity.

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 clause 'without loading full documents' implies this is for lightweight skimming rather than full retrieval, which hints at usage context. But it never names sibling alternatives (e.g., memory.read for full documents, memory.analyze for deeper analysis) or states explicit when-to-use/when-not-to-use conditions. Usage guidance is left to inference.

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