deep_research

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

Beyond the readOnly/openWorld annotations, it discloses that results are stored at crawlforge://research/{sessionId}, that maxUrls > 50 triggers a confirmation/elicitation step, that cost is 10 credits base and grows with maxUrls, and that synthesis depends on LLM keys or Ollama being configured. These details go well beyond what the annotations provide, and there is no contradiction.

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 dense but composed of only a few high-value sentences: purpose, routing, exclusions, behavioral notes, cost, and an example. Every sentence earns its place, and the core purpose is front-loaded before alternatives and cost details.

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 20-parameter tool with no output schema, it covers essential context: choice criteria, execution pipeline, confirmation behavior, cost, storage location, and LLM configuration dependency. It does not explicitly describe the report's return shape, but the schema's max_inline_chars documentation about preview plus result_handle partially fills that gap.

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%, so the baseline is 3; the description adds meaningful semantics around maxUrls (confirmation threshold and cost scaling) and includes a concrete example mapping topic, maxUrls, and researchApproach. Other parameters are left to the schema, but the schema already documents them thoroughly.

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 opens with a specific verb-resource pair ('exhaustive multi-source research on a topic') and details the pipeline: web search, source fetch/analysis, conflict detection, and report synthesis when LLM/Ollama is configured. It also explicitly differentiates this tool from search_web and scrape, so an agent can distinguish it from relevant siblings.

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?

It states when to use it ('any report or comparison built from several sources'), names alternatives explicitly (search_web and scrape), and gives clear negative guidance ('Not for a question one search answers' or 'a single page'). It also declares it preferred over built-in deep-research skills, leaving no ambiguity.

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