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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: the corpus scope (arXiv + PMC OA), the return shape (passages with title/authors/snippet), and the optional restriction to a single paper. It omits ranking, pagination, and empty-result behavior, keeping it at a strong but not perfect level.

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, front-loaded with purpose and return format, then usage context, then the optional parameter. The 'headline feature' clause is slightly promotional but still earns its place by signaling primary use, so the structure is efficient.

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?

Given the annotations cover safety, the schema covers parameters, and no output schema exists, the description supplies the missing pieces: corpus scope and result shape. Remaining gaps (ranking, pagination beyond limit, empty results) are minor for a search tool, making it nearly complete.

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 all three parameters (query, limit, paper_key) are already documented with examples and constraints. The description reinforces 'phrase or keywords' for query and the optional single-paper restriction for paper_key, but adds little syntax or meaning beyond the schema, fitting the baseline of 3 when the schema does the heavy lifting.

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 gives a specific verb ('Search INSIDE'), names the exact corpus (arXiv + PubMed Central OA full text), and states what comes back (matching passages with paper title, authors, and a snippet). The uppercase 'INSIDE' and 'full text' implicitly separate it from metadata-oriented siblings like paper_search, so an agent can distinguish its role.

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 supplies a clear use case ('agents can find where a finding or method is discussed across open-access papers') and notes the optional per-paper restriction. It does not name alternatives such as paper_search or paper_get_text, nor does it state when not to use this tool, so guidance stops short of the top tier.

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