删除事实条目

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

The destructiveHint annotation already declares the destructive nature, so the bar is lower. The description adds valuable context beyond the annotation: that clearing all facts leaves an empty profile shell that still surfaces in search/results, that there is no profile-deletion tool in this server, and that manual file deletion is the correct path for whole-profile removal. This meaningfully enriches the behavioral picture beyond the bare annotation.

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 appropriately wordy for the warnings it conveys — it's a single focused paragraph that packs when-to-use, when-not-to-use, and a strong misuse warning into a compact space. Every sentence earns its place; no filler or tautology.

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?

The tool is deceptively simple (2 params) but has a significant misuse pitfall (clearing whole profiles). The description thoroughly addresses this trap and the alternative path. An output schema exists, so return-value documentation isn't required. The only remaining gap is parameter-level detail (what factId looks like), but overall this is well-covered for a simple destructive action.

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 carries the full burden for explaining the two parameters. However, the description does not explain what factId and profileId refer to beyond their obvious names, nor the format/type of each. The concept of a 'fact' is implied by '事实条目' but never formally tied to the factId parameter. Given 0% coverage and only 2 simple parameters, the baseline should compensate, but the description adds minimal parameter-specific semantics.

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 states it deletes a single fact from a profile ('从画像中删除一条事实'), with a specific verb and resource. It distinguishes from siblings by explicitly contrasting with update_fact and warning against clearing entire profiles, though the sibling differentiation is embedded within usage warnings rather than a standalone purpose statement.

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?

Excellent guidance: explicitly states when to use (information confirmed incorrect or no longer relevant), when NOT to use (outdated info should use update_fact instead), and explicitly warns against using it to clear entire profiles. It also names the alternative tool (update_fact) and explains the consequence of misuse (a hollow shell that still appears in search and duplicate detection).

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