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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: month-bounded date windows, earliest supported date (2025-08-01), the scout_available flag signaling deeper analysis is requestable, and a retry_after_seconds/timeout protocol. These are exactly the operational traits an agent cannot infer from structured fields.

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?

Purpose is front-loaded and the remaining lines are dense, each carrying a distinct rule (concurrency, scout routing, date pairing, retry). It is slightly long and the scout sentence is split awkwardly across two lines, but no sentence is filler.

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 values need no explanation here; the description instead covers the decision-relevant edges — date bounds, concurrency, failure/retry, and escalation to get_scout. Nothing needed to invoke this tool correctly is missing.

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 75% and the description adds real meaning beyond it: from/to are UTC-inclusive, must be supplied as a pair, and each pair spans at most one calendar month; query should be English natural language with entities preserved. The limit parameter is left entirely to the schema, which is fine given its default/max are documented there.

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?

Opens with a specific verb+resource ('Discover indexed arXiv papers') and states the matching surface (titles, authors, abstracts) plus the goal (assess relevance). It also names the sibling get_scout and explains the relationship, so an agent can separate full-text search from deeper paper analysis without opening either 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?

Explicitly prescribes query formulation for broad questions ('consider distinct research dimensions and query each'), recommends 5-10 concurrent requests for batches, and routes to get_scout when deeper evidence is needed. It also gives clear exclusion-style rules for the date window ('provide both or neither', 'omit both for all indexed dates') and retry behavior on timeouts.

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