save_memory

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

With no annotations provided, the description carries the full burden and discloses the most important behavioral traits: content must be plaintext/human-readable, and providing dedup_key triggers automatic invalidation of prior facts matching (scope, subject, kind, dedup_key) while retaining the audit chain — indicating a soft-invalidate rather than physical delete. It does not cover duplicate behavior without dedup_key or response semantics, but the core side-effect contract is clearly stated.

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 short sentences with zero waste: purpose first, then the content constraint, then the dedup edge case. Every sentence adds distinct information and the most important behavioral caveat appears immediately after the purpose statement.

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?

For a 9-parameter tool with no output schema and no annotations, the description covers the core operation and the trickiest behavior (dedup invalidation), but leaves gaps: no return value or acknowledgment behavior, no statement about what happens when saving without dedup_key (are duplicates allowed?), and no mention of how valid_from, source, or confidence interact with the invalidation logic.

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 78%, so the schema already documents most parameters. The description adds real value beyond it: it specifies that content must be human-readable plaintext and, crucially, defines the invalidation matching tuple as (scope, subject, kind, dedup_key), which is more precise than the schema's vague '同键' (same key).

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 specific verb+resource ('写入一条记忆事实' / write a memory fact) that clearly establishes the create operation, distinguishing it from read siblings (search_memory, list_memories), mutation siblings (update_memory, forget_memory), and relation/consolidation siblings. The dedup_key invalidation sentence adds a signature behavior unique to this tool, making the purpose unambiguous.

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?

Usage is implied: call this when persisting a new memory fact, and reuse dedup_key to supersede an old fact while preserving the audit trail. However, there is no explicit guidance contrasting it with update_memory (modify existing facts) or forget_memory (remove facts), and no statement about when not to use it.

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