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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, and the description adds substantial extra context: 30-minute cursor rejection with HTTP 400, one bounded request with no background polling or automatic retry, metered/account-scoped access, affiliate 27 exclusion, and no guarantee of returns. It also warns that empty results do not imply lack of coverage.

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 purpose before the bootstrap/staleness detail, and most sentences carry operational information. It is dense and long, and fragments like 'Read-only Product data or price calculation' with an embedded line break read awkwardly and slightly dilute the otherwise tight structure.

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 delta-polling tool with an output schema already present, the description covers everything an agent needs: cursor acquisition, staleness rules, filtering semantics, polling strategy for live markets, and account/usage caveats. Return-value explanation is correctly delegated to the output schema.

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 reported schema coverage is 0% for the top-level query object, so the description must compensate, and it does: it explains last_id provenance and validity, the literal market_ids filtering with the 1,2,3,41,42,43 core-market expansion, and the affiliate_ids exclusion. Much of this also appears in the nested schema descriptions, so the added value over the schema is real but partly duplicative.

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+resource ('Get market price changes since a given ID', returns new/updated/closed market line changes) and names the intended use case ('efficient polling'). However, it never distinguishes itself from the closely named sibling v2GetDelta, so an agent cannot tell which delta endpoint to pick without opening both schemas.

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 states when to use it (polling for deltas), when not to bootstrap (only on known zero-delay access with a valid positive meta.delta_last_id, never substitute 0), what to do on cursor failure (one fresh scoped snapshot, no looping), and how to poll core live markets. This is unusually complete when/why/alternative guidance.

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