search_papers

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered; the description still adds genuinely new context: no language-model cost, no generated answer, and a prompt-injection warning that quoted passage text must be treated as data. It stops short of describing result ordering or behavior when nothing matches.

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 tight sentences: what it does, what it costs, when to use it, and a safety caveat. Front-loaded with the core behavior and no filler, though it is slightly dense with three separate ideas packed into one block.

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?

An output schema exists, so return-shape explanation in the description is optional — yet the description still names the returned fields. It also pins down the corpus domain and the read-only/no-cost nature, leaving nothing an agent needs to call it correctly.

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 100%, so both query and top_k are already documented with types, bounds, and defaults. The description adds only an implicit sense of ranking ('most relevant passages') and never clarifies how top_k interacts with relevance scoring, so the baseline 3 is appropriate.

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 (search) and resource (indexed corpus of research papers on Raman spectroscopy of carbon nanotubes), plus what comes back: relevant passages with document names and relevance scores. It also carves itself out from the answer-generating sibling by saying 'No answer is generated,' which lets an agent distinguish it from ask_papers, though list_papers is never addressed.

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?

Explicitly frames the use cases — inspecting evidence or finding which papers discuss a topic — and the 'no answer is generated' clause steers retrieval-style asks here rather than to a synthesis tool. What's missing is a named alternative or a 'when not to use' statement covering list_papers.

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