judge_evidence

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

With no annotations, the description must disclose behavioral traits. It reveals that the server handles evidence integrity, but it does not state whether the operation is read-only or mutating, whether it overwrites existing judgments, or what side effects occur. The phrase 'assign labels' suggests a write operation, but the description is silent on persistence, idempotency, or permission requirements. This is a significant gap for a tool without annotation coverage.

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 two sentences, front-loaded with the primary purpose and then clarifying role separation. Every word earns its place; there is no fluff or redundancy. It is compact while still delivering essential scope information.

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?

Despite having an output schema, its content is unknown. The description lacks details on how to construct the judgments array, the meaning of strength, whether research_id must correspond to an existing research, and what the response contains. The tool is moderately complex (nested array, multiple fields), and with no annotations, the description does not provide enough for an agent to call it correctly without additional inference.

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 0%, so the description must compensate for parameter meaning. The description does not mention research_id, judgments, or any field within EvidenceRelationJudgment. It only vaguely references 'relationship' and 'labels,' which does not clarify how to fill the required parameters or interpret strength. The schema itself provides the enum and default, but the description adds no additional semantic 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 tool's function: 'Assign bounded semantic relation labels to quote-verified evidence.' It identifies the specific verb ('assign'), the resource ('evidence'), and the scope ('bounded semantic relation labels'). It also distinguishes itself by clarifying the client's sole responsibility (classify relationship between quote and claim), which separates it from siblings like bind_evidence or assess_claims.

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 context about division of labor ('The server owns evidence IDs and quote integrity. The client does exactly one semantic task here'), implying when this tool is appropriate. However, it does not explicitly state when to use this tool versus alternatives, nor does it name any sibling or provide exclusion criteria. The guidance is implicit rather than explicit.

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