修改记忆

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

With no annotations available, the description carries the burden of behavioral disclosure and does so well: it explains partial-update semantics (unspecified fields stay unchanged), clearing semantics for project/task_type/category, and the trust-reset side effect of substantive content rewrites. The mention of 'user_notice 原样转述' is problematic because user_notice is not a schema property and additionalProperties is false, creating confusion.

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 compact and front-loaded: a quick list of what can be updated followed by three high-value behavioral caveats. The user_notice sentence is tangential and slightly dilutes focus, but otherwise every sentence contributes.

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 mutation tool with no annotations and no output schema, the description covers the key operational context: user approval, field-unchanged behavior, clear semantics, and trust reset. It omits explicit explanations of the two policy enums and does not describe the return/confirmation payload, leaving some gaps but overall enough for an agent to call it correctly.

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 only 11%, so the description must compensate; it does add useful meaning for partial updates, clearing, and trust reset. However, it does not explain the semantics of risk, confirm_policy, or unattended_policy beyond what the enum values imply, and the user_notice comment references a non-existent parameter.

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 identifies the action ('Update/修改') and resource ('a preset'), and enumerates the categories of changes (content, scope, classification, policy, status). This distinguishes it from the sibling tools that list, recall, delete, or consolidate memories, though the Chinese title '修改记忆' could be slightly ambiguous until the description clarifies 'preset'.

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 states an important precondition: the modification must already be user-confirmed ('需用户已确认该修改'), which helps an agent know when it is appropriate to call the tool. However, it does not explicitly name alternatives or exclusion conditions, so an agent must infer when to prefer recall_presets, save_requirement, or delete_memory instead.

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