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

Adds substantial context beyond annotations: consumes Growth Credits, output is gated by the owner's approval settings so nothing goes public from this call, and the operation is long-running/asynchronous. The openWorldHint=false annotation is consistent with 'nothing goes public from this call', so no contradiction.

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 what happens and examples, then behavior and cost. Every sentence carries information (cost, approval gate, latency, follow-up). Slightly dense but no filler; the multiple short clauses read choppier than necessary.

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 single-param, no-output-schema, async mutation, the description covers cost, approval gating, visibility, latency, and the recommended follow-up tool. Minor gaps: what happens if credits are insufficient and what an error response looks like. Overall sufficient to invoke correctly.

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% and the single parameter is documented as 'What the owner wants, in their words.' The description goes further by giving two worked examples that show the appropriate register and scope of the instruction, which is genuinely useful for a free-text field with a 600-char cap.

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 outcome chain: takes an instruction, 'sets the focus, writes the strategy and queues the work,' with two concrete example instructions. An agent can tell this is the campaign-creation entry point. It doesn't explicitly contrast with ask_growthdept or other siblings, which is why it falls short of a 5.

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?

The two example instructions ('Launch a campaign for house removals in Lewisham', 'Get more enquiries this month') show the expected input shape and level of abstraction. It also tells the agent to read whats_happening shortly after if the answer says started. Missing: any explicit 'when not to use this' or a named alternative such as ask_growthdept for questions.

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