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

Annotations declare idempotentHint/readOnlyHint=false, and the description goes well beyond them: it discloses that the call queues durable async jobs, that it never returns fabricated completed data, the credit cost model (X requires expectedCredits equal to creditsPerRefresh, other channels cost zero workspace credits), and the idempotencyKey reuse contract. That is exactly the extra behavioral context annotations cannot carry.

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?

Five compact sentences, front-loaded with the purpose and the precondition; no filler. Slightly telegraphic phrasing, but every sentence carries an operational constraint.

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?

Output schema exists, so return-value explanation is rightly omitted, and the description still covers the prerequisites, credit preconditions, async queue semantics and follow-up polling step. The only real gap is that the meaning/effect of the days and kind defaults (content vs daily vs all) is not conveyed.

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 0% across 6 parameters, so the description must compensate. It adds real meaning for expectedCredits (equals creditsPerRefresh for X), kind (must be 'all' for X) and idempotencyKey (reuse with same arguments), but leaves days, brandId and accountId entirely unexplained. Partial compensation warrants a mid score.

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 (request a fresh report for one connected channel) and immediately differentiates from siblings by positioning it as the queueing counterpart to get_channel_report and the generic sibling to request_x_report. An agent can tell what it is without opening the 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?

Explicit gating: 'only when the user asks' and 'Read get_report_capabilities first', plus a named polling alternative (get_channel_report). This is the when/when-not/prerequisite pattern in compressed form.

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