追加事实条目

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose the deduplication behavior (facts matching existing content are skipped and reported in skipped) and the anti-contradiction guidance. However, it does not mention potential issues like append-only semantics, whether facts are immutable, or return structure beyond skipped. Still, the dedup and skip reporting are meaningful disclosures given zero annotations.

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 — two sentences total — and every sentence earns its place. The first sentence states the primary function and dedup behavior; the second provides the critical alternative-tool guidance. No filler, no redundancy, and the most important differentiating guidance is front-loaded in the correction sentence.

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?

Given a well-structured schema (enum categories, confidence with default) and an output schema, the description covers what's most critical beyond the schema: dedup behavior and correction routing. It lacks some depth around edge cases (e.g., what 'skipped' means structurally, whether the tool returns the created fact IDs), but for a moderate-complexity tool with strong schema support, this is adequate-to-good. The correction routing is the highest-value missing-schema context and it's present.

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%, so the description must compensate. It explains the semantic concept of facts (content added to a profile) and the dedup behavior, but does not detail the individual parameters (profileId, facts, category, source, confidence). However, the schema itself is richly self-descriptive with enums and defaults for category and confidence, so the schema does the heavy lifting for parameter semantics. The description adds the behavioral meaning around dedup and correction.

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 the verb (append facts), the resource (existing profile), and key behaviors (deduplication via skipped reporting, correction handling via update_fact). It explicitly distinguishes the tool from the sibling update_fact by clarifying that corrections should use the sibling instead. The scope and behavior are specific and immediately actionable.

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 explicitly states when to use this tool (appending new facts to an existing profile), and provides a clear exclusion: if the fact is a correction (e.g., job change), use update_fact instead to avoid contradictory entries. It names the sibling tool and explains the rationale, giving the agent concrete decision guidance.

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