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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the agent knows this is a non-read-only, non-destructive, closed-world operation. The description adds only 'RETURNS: 综述文本' and says nothing about what the non-read-only behavior writes, whether output is persisted, how long/comprehensive the review is, or whether citations are included — meaningful gaps given readOnlyHint=false.

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, label-prefixed format is front-loaded and scannable, and every section (use-when, aliases, returns) is functional. The alias list is long relative to the rest but serves genuine matching value; no filler prose.

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 four-parameter generative tool with no output schema, the definition covers trigger, aliases and a one-phrase return note, which is enough to select it. It is thin on what the produced review looks like (length, structure, citation handling) and on the fact that it is not a pure read operation, both of which an agent would need to set expectations.

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%, with all four parameters (研究主题, 研究问题, 人群, 干预) documented in the schema, so the baseline is 3. The description adds no guidance beyond the schema, such as whether question/population/intervention are optional refinements that narrow scope or how they change the generated review.

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 states a specific verb+resource: produce a literature review / state-of-the-art summary for a topic. It is unambiguous about what is produced, but it does not distinguish itself from plausible siblings such as literature_review_outline or systematic_review_assist, so an agent cannot route between them on this text alone.

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 explicit 'USE WHEN: the user wants a literature review or state-of-the-art summary for a topic' gives a clear trigger condition, and the alias list (文献综述, 研究现状, 综述, state of the art) helps match user phrasing. It stops short of stating when NOT to use it or naming the alternative tool for outline-only or systematic-review workflows.

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