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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=true. The description adds substantive behavior beyond that: a mandatory human-approval gate, a required second invocation, and the fact that the mobile pipeline never receives a plan and starts immediately with no URL. These are operational facts an agent could not infer otherwise.

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 action, then the critical approval requirement, then the exception. Dense but every clause carries operational information; the mobile sentence is long yet justified because it prevents a wrong branch of behavior.

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 11-parameter, multi-step, open-world tool with no output schema, the description covers the critical decision points: the approval loop and the mobile branch. Gaps remain around what the first call returns and how the crawl-tuning parameters (depth, pages_limit, framework) affect the run.

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 36% schema description coverage across 11 parameters, the description compensates only partially: it explains approved_virtual_test_plan's role and the second-call requirement, and clarifies that url is unnecessary for mobile. It says nothing about depth, pages_limit, framework, test_type, enable_giskard_validation, or what the first call returns as the plan object.

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 and resource ('Start an AI crawl job') and distinguishes itself by saying it uses 'an existing test case as instructions', which separates it from the sibling start_ai_crawl. It never names start_ai_crawl explicitly, so the differentiation is implicit rather than spelled out.

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 prescribes the two-call workflow: first call generates a virtual test plan, the agent must present it to the user, wait for approval, then re-call with approved_virtual_test_plan. It also names the precise exception (Native Mobile project) and its different behavior, leaving no ambiguity about when this tool applies or how to sequence it.

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