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

Annotations only say readOnlyHint=false and openWorldHint=false; the description adds the material side effects: a 14-day trial begins, an API key and tracking script are issued, and the billing contact receives an out-of-band email with a claim link and card prompt. It also discloses that no API key is required for the call itself, which is the auth-model detail an agent most needs.

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?

Two dense sentences, front-loaded with the action and then the lifecycle and side effects. Every clause carries information an agent needs (trial length, returned credentials, claim flow, no-key access) with no filler.

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 nested-object, no-output-schema mutation tool, the description covers the account lifecycle and the pre-claim state well, so an agent knows the account is not fully usable until billing claims it. Gaps remain around the `site`/`agent` object semantics and failure modes (e.g. duplicate domain or invalid domain), but the core behavior is complete.

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 description coverage is only 25%: the `site` object (with required `domain`) and `billing_contact_name` are undocumented, and the description compensates for none of them. What it does say about the billing contact ('emailed a link to claim the account and add a card') largely restates the schema's own description of billing_contact_email, so it adds little beyond structured data.

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 ('Create a Measure account') and immediately qualifies the unusual agent-initiated variant ('without a human'). It also names the concrete outputs (API key, tracking script, claim email), so an agent knows exactly what this does and what it yields, with no sibling tool in the list offering anything similar.

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?

'Without a human' plus 'No API key needed' tells the agent this is the unauthenticated, agent-driven entry point, which is the key selection condition. It stops short of explicit when-not guidance (e.g. what to do if an account already exists, or which sibling to use after signup), leaving that to inference.

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