agent

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

With no annotations provided, the description carries full burden. It details the pipeline (plan, search+fetch in parallel, optional extraction, synthesis), mentions full step transparency via steps[], explains LLM-optional behavior, and discloses fallback to keyword extraction. It also covers budget and output controls.

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 high-level summary, LLM-optional note, parameter details, pipeline, and return value list. It is front-loaded with purpose. However, it is somewhat lengthy and includes minor details (e.g., tokenizer drift) that could be omitted for 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?

Given the complexity (9 parameters, nested objects, no output schema), the description is thorough. It explains the pipeline, behavior without synthesis LLM, return fields (result, sources[], steps[], etc.), and parameter effects. It covers edge cases like max_tokens_out vs max_chars and citation format options.

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 coverage is 100%, and the description adds significant value beyond the schema. It explains the purpose of each key parameter in context (e.g., 'prompt: NL description of what to gather'), provides defaults (max_pages=10, max_time_ms=60000), and describes citation_format options with examples.

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 starts with 'Natural-language data gathering across sources', clearly stating the verb (gather) and resource (sources). It distinguishes the tool from siblings like fetch and search by describing a multi-step pipeline (plan, parallel fetch, extract, synthesize).

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 explains when to use this tool (for NL data gathering with optional schema) and provides context for LLM-optional behavior. It tells the agent to configure an LLM key for best results and warns against presenting raw step logs. However, it does not explicitly list when not to use it or compare directly to siblings.

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