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

Annotations only declare readOnlyHint=false; the description carries the real behavioral load by disclosing the quota (10 requests per UTC day), per-network and capacity limits, and critically that the key is shown only once and is a credential to be saved. That is exactly the kind of one-shot, unrecoverable-output warning an agent needs before calling.

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?

Four compact sentences, front-loaded with what is returned, followed by limits and the one-time-display warning. No filler; each sentence carries a constraint or a warning the caller must act on.

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 output schema, the description fully covers what comes back (the key, displayed once), the quotas, the eligibility limits, and the credential handling requirement. An agent has everything needed to invoke this correctly and to warn the user.

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?

The tool takes no parameters, so the schema has nothing to document and the baseline is 4. The description's mention of 'one user-chosen watched GOV.UK page' hints at a downstream choice but does not introduce parameters that do not exist.

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: request an instant 3-day trial API key, with the exact scope (10 requests per UTC day, one watched page). This is clearly distinguishable from siblings like watch_govuk_page or fixed_monitored_pages, which operate on existing keys/watches.

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?

Gives explicit when-not guidance ('Do not request repeated trials', 'One trial per client network address, subject to daily capacity'), which is stronger than most. It stops short of naming an alternative for users who already have a key (e.g., watch_govuk_page), so it is clear context without full routing.

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