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

The description discloses that the tool returns a list of POI details (store names and coordinates) and explicitly states it does not answer count/density questions, which is a behavioral limitation. It also mentions optional parameter extraction from input_text. The annotation only provides openWorldHint, no contradicting information, so no annotation contradiction.

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 concise, using a single paragraph with examples and a separate pricing note, but it includes a redundant pricing section (credits per data unit) that is not directly relevant to functionality for an agent. Structure is clear and front-loaded with the core purpose, but the extra pricing info slightly reduces conciseness.

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 description provides sufficient context for an agent: it explains the input requirements (city/district, optional parameters), the output nature (detailed list with names/coordinates), and a clear limitation (no counts). No output schema is provided, but the description covers the essentials. Given the tool's simplicity, this is adequately complete, with a small deduction for not mentioning potential pagination or result size.

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?

All four parameters (version, gov_name, poi_type, input_text) have descriptions in the schema, providing 100% coverage. The tool description adds semantic value by explaining that parameters are optional and will be extracted from input_text if omitted, and clarifies the meaning of poi_type (e.g., metro station or code). This goes beyond the schema's basic descriptions, justifying a score above baseline.

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 tool's function: querying detailed dining POI lists (store names and coordinates) within a specified city or district. It specifies covered categories (Chinese restaurants, fast food, cafes, etc.) and provides typical usage examples, effectively distinguishing it from sibling poi_data_* tools by focusing on dining.

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 indicates usage based on explicit city/district names and includes typical question patterns, implying when to use it. It does not explicitly contrast with alternatives (e.g., other poi types), but the domain-specific nature (dining) and examples make usage clear. A slight deduction for lack of explicit exclusion of non-dining POI queries.

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