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

Goes well beyond the annotations: it discloses that the call queues durable jobs rather than returning data, that it never returns fabricated completed results, the per-channel credit cost model (X requires expectedCredits equal to creditsPerRefresh with kind all; other channels cost zero workspace credits), and the idempotencyKey reuse contract. The idempotency and async-job behavior is exactly the context an agent needs and annotations alone cannot convey.

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-loads the purpose and the 'only when the user asks' gate, then packs prerequisites, credit rules, idempotency and polling into terse imperative clauses. Dense but essentially waste-free; slightly telegraphic in places, which costs it the top mark.

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 an async, credit-consuming, idempotent job tool this covers the full lifecycle: prerequisite read, submission rule, credit/pricing caveat, retry semantics, and how to retrieve results. An output schema exists so return-shape detail is unnecessary; only the sibling overlap with request_x_report is left unaddressed.

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?

With 0% schema description coverage the description must carry parameter meaning, and it does for the hardest ones: expectedCredits (must equal creditsPerRefresh for X), kind (must be 'all' for X), and idempotencyKey (reuse with identical arguments). brandId, accountId and days are left to their schema types, so coverage is strong but not complete.

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 and scope: 'Request a fresh report for one connected channel'. It also separates itself from the related read/poll tool by naming get_channel_report for status/results, so an agent can route 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?

Gives a clear activation condition ('only when the user asks') and a prerequisite ('Read get_report_capabilities first'), plus the follow-up step (poll get_channel_report). It does not, however, clarify the boundary against the sibling request_x_report, even though this tool also handles X-specific credit rules, leaving a real ambiguity unresolved.

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