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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false; the description corroborates this by stating it 'opens nothing by itself', clarifying that this call has no side effects and no live data access. It also adds genuinely useful external constraints (Housecall Pro API is MAX-plan only with a limited-access key, checked 14 Oct 2026), which no annotation conveys. What it does not disclose is the shape or size of the returned guidance, though the '(screens, buttons, fields)' parenthetical partly covers that.

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?

Three sentences with little waste, but the ordering is counterproductive: the lead sentence sets a false expectation (listing customers) before the correction appears. The dated API-plan note is relevant but reads as an appended aside rather than front-loaded guidance.

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?

With no parameters and no output schema, the description must carry the whole burden of explaining what comes back, and it only sketches this ('how to do it step by step (screens, buttons, fields)'). The handoff to cotlet_browser_* tools is stated but the agent isn't told how the returned steps map onto those tools, leaving a gap for a 0-param, no-output-schema tool that exists purely to produce procedural content.

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?

There are zero parameters and the schema is an empty object, so there is no parameter semantics to explain; baseline 4 applies. The description correctly implies a no-argument call by saying it 'opens nothing by itself'.

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 opening sentence claims to 'List customers in the user's own Housecall Pro account', but the second sentence reveals the tool actually returns step-by-step instructions for doing it manually. The real behavior is stated ('Returns how to do it in Housecall Pro step by step (screens, buttons, fields)'), so an agent can eventually figure it out, but the name/title and first sentence point at a data-retrieval tool rather than a guide, which muddies purpose against siblings like list_customers.

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?

It gives a concrete follow-up path ('then do it with the cotlet_browser_* tools in the user's Housecall Pro Cloud Browser') and negatives ('opens nothing by itself'), which is real usage context. However, it never says when to choose this over the sibling list_customers tool, so the agent is left to infer whether this or the plain list tool should be used for the same intent.

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