create_research_brief

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

With no annotations supplied, the description carries the full burden and does real work: it discloses the multi-source resolution order with a conditional ("WoS Expanded (when configured)") plus fallbacks to Scopus, OpenAlex, and Crossref, and it states the returned payload (abstract, keywords, references, citing sample, brief_id). Gaps remain around failure behavior when a seed cannot be resolved and around whether the brief_id implies persisted server-side state.

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?

Two sentences, zero filler, with the purpose front-loaded and the return contract following. Every clause adds information an agent would otherwise lack.

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?

No output schema exists, so the description must describe returns, and it does so concretely for a 5-parameter nested-schema tool. The main shortfall is the undocumented nested scope object, which an agent could easily populate incorrectly given no field-level guidance anywhere.

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 60%, and the description adds little beyond it: the seed and intent parameters are only echoed, and focus, scope, and includeCitationContext are never explained in the description – the nested scope object (years, regions, discipline, exclusions) has no schema descriptions at all. The mention of "citing sample" loosely maps to includeCitationContext but gives no notion of the bound or cost of enabling it.

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?

States a specific verb and resource ("Create a research brief") and immediately names the inputs (seed paper plus user intent), then enumerates the artifact returned. This clearly separates it from the search_* siblings, which only retrieve records rather than producing a persistent brief with a brief_id.

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 phrase "from a seed paper plus the user intent" and "a brief_id for later searches" tells the agent this is the entry point when a known paper anchors the investigation and downstream searches will follow. It does not explicitly say when to prefer search_papers or get_paper_by_doi instead (e.g., when no seed exists), so the exclusion side of the guidance is left implicit.

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