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

The description discloses that the tool returns periodic changes (周期变化) and lists the metrics it covers, which is useful behavioral context. The annotations include only openWorldHint, which does not indicate safety or side effects. The description does not contradict annotations, but it adds limited transparency about potential side effects, required auth, or error handling. Given the tool is a query, the burden is moderate, so a score of 3 is appropriate.

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 well-structured with a clear main purpose, a list of included metrics, exclusions, and examples. It is slightly verbose but each section adds value. The pricing info is included but does not detract. It is front-loaded with the main purpose, making it easy for an agent to quickly assess. Minor trimming could improve conciseness, but it is generally effective.

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 description covers the core functionality, including the exact indicators, exclusions, and examples. With only two parameters and high schema coverage, the description is sufficient for the complexity level. The presence of an output schema (not shown) likely specifies return structure, so the description does not need to explain that. It could include time-range details or interpretation hints, but these are not essential given the scope.

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?

The schema already provides descriptions for both parameters (company_name and country_name), and the coverage is 100%. The description adds example values and clarifies that company_name should be a specific enterprise name, but it does not provide additional semantic information beyond the schema. Since the schema handles the parameters well, the description meets the baseline without significant added value.

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 purpose: to query periodic changes in environmental responsibility indicators for a specific company, naming the exact metrics (green investment, energy savings, carbon emissions, etc.). It distinguishes itself from sibling tools by specifying the domain (environmental) and explicitly stating what it does NOT cover (certifications, batch screening). Examples of typical queries further reinforce the purpose.

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 provides clear guidelines on when to use the tool by listing exclusions (not for certification queries, not for batch filtering by park/industry chain) and giving example queries to illustrate appropriate usage. However, it does not explicitly name alternative sibling tools (e.g., enterprise_change_certification) for comparison, which would make the guidance even stronger.

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