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

With no annotations, the description carries the full burden and does most of it: it discloses a per-query price (€0.002), the exact billing identity (the API key in Authorization: Bearer), and that no PDFs are fetched. That is real operational context an agent needs before calling. Missing are rate limits and what happens on auth failure, so it falls short of a 5.

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?

Front-loaded with the core verb and mechanism, then progressively more operational detail — cost, auth, parameters. Dense but every clause adds something. The trailing parameter list reads as a run-on sentence rather than a formatted block, which costs a little scanability.

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 three-parameter paid search tool, the coverage is solid: cost, auth, corpus limits and all parameter meanings are stated, and an output schema exists so return values need no prose. The gap is edge behavior — all three parameters are nullable with no required fields, and the description never says what a null query returns or how empty results are signalled.

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 0%, so the description must supply all parameter meaning, and it does: free-text query, an optional arXiv category filter with a concrete example (cs.CL), and max_results bounded 1-20 with default 5. One caution — the schema types max_results as a nullable string while the description describes it numerically, so the description usefully corrects the schema but leaves the type ambiguity unresolved.

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?

"Searches arXiv metadata and reranks results by embedding similarity to the query" names a specific verb, a specific corpus (arXiv), and the retrieval strategy (embedding rerank), then enumerates the returned fields. This clearly separates it from generic siblings such as web_search, semantic_search and lib_docs without the agent needing to open a schema.

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 scopes the tool well ("Metadata and abstracts only — PDFs are never downloaded"), which tells the agent this is not a full-text reader. However, it never states when to prefer this over sibling tools like web_search or semantic_search, nor when not to use it. A "for full text use X" routing sentence is the missing piece.

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