screen_sources

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It does not state whether the tool is read-only or mutates state, what side effects it has, whether it returns results or just records them, or any permission requirements. The word 'gate' implies filtering but gives no concrete behavior.

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 a single short sentence, so it is concise. However, it is not front-loaded with actionable information; the metaphor obscures rather than clarifies. It is under-specified, which is not effective conciseness. The structure is minimal but at the expense of clarity.

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?

For a tool with a nested object schema, enums, and no output schema, the description is severely incomplete. It does not explain the tool's purpose, inputs, expected outputs, or relationship to the broader research workflow. An agent would have to guess at nearly every aspect of how to call it correctly. The description is inadequate for the tool's complexity.

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%, and the description provides zero explanation of the two parameters. It does not mention research_id or screenings, nor the nested structure with source_id, verdict, and reason. The enum values (RELEVANT, PARTIAL, IRRELEVANT) are unexplained. The description adds no semantic value beyond the raw schema titles.

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 uses the vague metaphor 'semantic source gate' without defining what it means or stating the tool's actual function. It does not explicitly say that it screens sources against a research question and assigns verdicts (RELEVANT/PARTIAL/IRRELEVANT). The purpose is only loosely inferable from the tool name, and it does not differentiate from siblings like review_candidates or get_source_context.

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 gives no guidance on when to use this tool versus alternatives. It hints that it operates on a 'server-provided review shortlist' but does not state prerequisites, conditions, or exclusions. There is no mention of when this should be called relative to other steps in the workflow, such as after discovery_search or before judge_evidence.

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