search_literature

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: deduplication across sources, source provenance, a returned search_id, and the default inclusion of WoS when configured. Quota behavior is only hinted at through the schema's layer note, and there is no discussion of auth or rate limits.

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?

Three dense sentences, front-loaded with the platform list and the return shape, then workflow guidance. No filler, though the subagent-delegation sentence sits slightly apart from the core tool description.

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 14-parameter tool with no annotations and no output schema, the description explains what comes back (provenance + search_id) and how to sequence layers, which is useful. It does not cover the filter/pagination parameters or any quota details an agent would need to call it efficiently.

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 only 36% of 14 parameters, so the description should compensate. It adds real meaning for layer (triage vs screening vs evidence packets) and implicitly for mode, but leaves year, author, journal, sources, sortBy/sortOrder, perSource, maxResults, and openAccess undocumented in both schema and description.

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 ('unified deduplicated literature search across WoS, Scopus, OpenAlex, and Crossref') plus the return shape ('candidates with source provenance and a search_id'). This clearly differentiates it from the per-source siblings such as search_scopus, search_crossref, and search_openalex.

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?

Gives concrete when-to-use guidance for the layer parameter: metadata for cheap triage, abstract for screening, evidence for deeper packets, and recommends delegating screening to batched subagents. It stops short of explicitly saying when to use this tool versus the individual per-source search tools in the sibling list.

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