recall

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

Annotations declare readOnlyHint=false, which could confuse an agent about a search tool; the description resolves this by explaining that search 'records the query and accessed memory IDs in local activity history for auditability; it does not rewrite stored knowledge.' It also discloses the rerank latency tradeoff and the WENLAN_RERANKER_ENABLED=1 daemon prerequisite with its silent fallback behavior — none of which the annotations or schema fully capture.

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?

Front-loads purpose and triggers, then layers query-writing advice, filtering strategy, and the rerank tradeoff in short scannable sentences. It runs a bit long for a search tool, and the rerank detail is partially redundant with the schema's own description of that parameter, but no sentence is wasted.

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?

Six parameters with an unusual audit side effect and a feature-gated quality flag demand more than a one-liner. The description covers trigger conditions, query formulation, filter-vs-query tradeoff, the side effect that explains the write-ish annotation, and the sibling boundary — enough for correct invocation without an output schema.

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 100%, so baseline is 3, but the description adds real strategy beyond the schema: write queries as natural language because the engine does semantic matching, and prefer filters over longer queries when result sets are too large. The rerank flag's prerequisite is restated with its failure mode, though per-parameter meanings live mostly in the schema.

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?

Opens with a specific verb+resource ('Search memories by query') and immediately differentiates from the closest sibling: 'To resume work from a Space-owned project snapshot, use brief instead.' An agent can route correctly without opening either 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?

Gives concrete triggering phrases ('do you remember', 'what do you know about', 'look up') plus the proactive condition 'when you need a specific fact before acting.' It also names the alternative tool and the condition that selects it, and explains the fallback strategy (add filters rather than lengthen the query) when results are too broad.

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