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

With no annotations, the description carries the full burden and does so well: it discloses the 20 calls/minute rate limit, that group_by 'feature' spends 8 and 'extraction_type' 11 of those, that costs are in the currency's main unit with one entry per currency, the default 7-day window, and that only recorded usage is covered. This is unusually rich behavioral context for a read tool.

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?

The purpose and grouping/filter capabilities are front-loaded in the first sentence, followed by limitations and rate limits. It is dense and reads as two very long sentences, which slightly hurts scanability, but essentially every clause carries operational information.

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 12-parameter analytics tool with no output schema, the description covers the window, grouping modes, filter dimensions, currency semantics, limitations, and rate-limit cost of expensive group_by values. The row-per-bucket semantics are also spelled out in the schema, so nothing an agent needs to call it 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 coverage is 100%, so the baseline is 3, but the description adds real meaning beyond it: the expected 'tag:value' filter syntax, that domain grouping is sorted by cost, and the conceptual mapping of each filter dimension. It stops short of explaining defaults for every filter, keeping it at 4.

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 ('Recorded Zyte API usage of the organization') and enumerates the exact metrics returned (requests, cost, response times, status codes). It explicitly distinguishes itself from siblings by naming zyte_api_domain_pricing and ruling out Scrapy Cloud jobs, so an agent can route without opening 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?

Gives explicit when-to-use (historical usage over a time window with grouping/filtering) and when-not ('cannot estimate a future crawl – use zyte_api_domain_pricing'; 'knows nothing about Scrapy Cloud jobs'). It also warns not to repeat expensive group_by calls within a minute, which is actionable routing guidance.

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