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

Goes well beyond the annotations (readOnly=false, openWorld=true, idempotent=false, destructive=false) by disclosing the pre-acceptance quota check, refusal semantics with billing code and no audit created, billing counting ('one audit.capture per page captured', failed pages count nothing), and the eventual-consistency detail ('when it finishes'). This is unusually rich and directly actionable behavioral context.

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 action, then behavior, then the polling handoff, with no padding. The middle sentences ('the product admits its page bound against the organisation's usage') are dense and grammatically strained, slightly reducing readability, but every sentence earns its place.

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 quota-gated create tool with no output schema, the description covers preconditions, refusal, billing impact, and follow-up well. It stops short of stating what is returned on success (e.g., an audit identifier), leaning on the poll pointer instead, which is a minor gap.

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 50% (reason is documented in-schema; site_id is not), so the bar is roughly baseline. The description implies single-site scope ('one site') but adds no syntax or constraint detail for site_id or reason beyond what the schema already carries, so it neither compensates nor detracts.

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?

The first sentence gives a specific verb and resource with scope: 'Start a manual audit of one site now.' It also names the sibling it hands off to ('Poll audit.audit.get for progress'), so an agent can separate creation from progress retrieval 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?

Usage is implied through the operational preconditions (page bound vs. org usage, refusal on exhaustion) and the pointer to audit.audit.get for polling. However, there is no explicit when-to-use/when-not-to-use guidance or comparison against other audit.* creation/listing tools, leaving selection mostly to inference.

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