读取招聘源图谱 / Read source graph

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

Annotations already indicate readOnlyHint, idempotentHint, and destructiveHint. The description adds that it is 'paginated' and returns 'evidence-bearing relations', which is useful context about the nature of the output. However, it does not disclose other behavioral aspects like auth requirements, cursor handling behavior, or any specific limitations. Since annotations provide the core safety profile, the description's extra detail is beneficial but not extensive.

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 and to the point. It consists of two short sentences (bilingual) that effectively convey the action and resource. No verbose or redundant content.

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?

Given that the tool has an output schema and involves four optional parameters, the description provides the core idea (reading relations) but lacks explanation of the parameters and pagination logic. It is sufficient for a simple, safe, read-only operation, but for an agent to correctly filter or paginate, more context would be necessary.

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 input schema has no descriptions for any of the 4 parameters (schema coverage 0%). The description does not explicitly explain `cursor`, `limit`, `source_id`, or `relation_type`. Although it lists the relation types that likely correspond to `relation_type` values (e.g., source, region, etc.), it does not explicitly instruct the agent on how to use these parameters. The description fails to compensate for the lack of schema-level documentation.

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 action: '分页读取' (paginated read) with a specific resource: the evidence-bearing source graph relations. It enumerates the entity types involved (发布主体、来源、地区、入口、端点、发现渠道与岗位), which distinguishes it from sibling tools like list_sources or discover_sources, which deal with sources themselves rather than relational data.

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 does not provide any guidance on when to use this tool vs alternatives. It only states what it does, with no mention of scenarios, exclusions, or explicit comparisons to similar readings (e.g., when to use 'source graph' vs 'list_sources'). This leaves the agent to infer the applicability.

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