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

Annotations already declare the tool read-only, idempotent, non-destructive, and open-world. The description adds useful behavioral context beyond that: the corpus composition, that results are passages rather than whole papers, and that the search can be narrowed to a single paper. It does not cover response edge cases, but the annotation coverage lowers the bar.

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 sentences with no filler: the first states the core capability and return shape, the second gives the headline use case, and the third notes the optional restriction. The most decision-relevant information is front-loaded.

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 search tool with only 3 parameters, no output schema, and safety fully covered by annotations, the description is complete. It tells the agent what corpus is searched, what the results look like, and how to narrow by paper_key, while the schema covers limit and required query. Nothing essential is missing for correct invocation.

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?

The input schema covers all parameters at 100% and already documents query, limit, and paper_key with examples. The description's mention of 'phrase or keywords' and optional paper_key restriction largely restates the schema, adding little new semantic value. 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?

The description opens with a specific verb ('Search INSIDE') and names the exact resource: an indexed open-access corpus of arXiv and PubMed Central OA full text. It also states the output form—matching passages with paper title, authors, and snippet—which clearly differentiates it from sibling tools like paper_search or paper_details.

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 this is the headline feature for finding where a finding or method is discussed across open-access papers, which gives the agent a clear use case. It does not explicitly name alternatives or say when not to use this tool, but the 'search inside full text' framing and optional paper_key restriction imply the appropriate context.

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