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

Annotations already declare destructiveHint=false and openWorldHint=false, so the safety profile is largely covered. The description adds the input modality (pasted text) and that output is structured PICO, but not what the PICO fields look like or whether anything is persisted — notable given readOnlyHint=false on what reads as a pure extraction tool.

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 sections are front-loaded with purpose, then trigger, aliases, and return. The alias list is bulky, but aliases serve retrieval and the whole definition is short enough that nothing is wasted.

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?

With one parameter, no nested objects, and no output schema, the tool is simple enough that the description is nearly sufficient. However, 'RETURNS: 结构化 PICO' is the only statement about output and does not tell the agent what structure to expect or how to handle low-confidence extractions.

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 100% with a single parameter documented as '文献文本'. The description adds only marginal meaning by indicating the text should be an abstract or paragraph, which does help calibrate input length, but gives no size limits or formatting expectations.

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 name and description state a specific verb and resource: extract PICO from pasted text. The 'from pasted text' qualifier gives a scoping hint that plausibly separates it from PICO siblings like pico_refine or pico_structure, but the description never names or contrasts those siblings explicitly.

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 'USE WHEN: the user pastes an abstract or paragraph and wants PICO extracted from it' clause gives a clear trigger condition tied to the user's action. It stops short of stating exclusions or which alternative to pick when the input is a file, a full PDF, or an already-partial PICO.

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