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

Annotations mark this as non-read-only, non-destructive, and non-open-world, which is a slightly unusual profile for what appears to be a literature-expansion tool; the description says nothing about why a write hint is set or what state, if any, is modified. It also stays silent on cost, latency, or what happens when topic is a single ambiguous token. The stated return ('扩展研究方向') is the only behavioral disclosure beyond the structured fields.

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 pipe-delimited USE WHEN / ALIASES / RETURNS layout front-loads the trigger where an agent will read it first, with no filler prose. The alias list is long relative to the substance and duplicates the Chinese and English title, which costs a point but not much clarity.

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?

There is no output schema, so the description must characterize what comes back, and '扩展研究方向' is thin for a tool that also returns up to 25 papers and optional body sections. Nothing explains how the returned directions relate to the returned literature or what shape the expansion takes. An agent could call it, but not set expectations for the caller.

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 100%, so the schema already documents topic, max_papers (default 5, hard cap 25), and include_sections semantics. The description adds no parameter meaning beyond that and does not explain how a one-word topic influences paper retrieval. Baseline 3 is appropriate.

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 names a specific verb+resource: expand a vague word or hunch into researchable directions, and the USE WHEN clause tells an agent immediately what class of request this tool serves. It is distinguishable from siblings like academic_polish or design_type_decision. It loses a point because the 'RETURNS: 扩展研究方向' line omits the literature-retrieval behavior that the schema (max_papers, include_sections) clearly implies.

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?

There is an explicit, well-bounded trigger: 'the user gives one vague word or a hunch and wants it expanded.' The bilingual alias list widens recognition of that trigger. However, it gives no when-NOT-to-use guidance and does not point to any sibling for cases where the user already has a concrete topic.

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