Start/stop monitoring

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds that this is a scheduled/ongoing operation, that it creates the history get_changes reads, and that it requires a paid subscription with trial details. It also handles the fallback behavior for non-subscribers. It does not spell out whether stopping is reversible or what happens to existing history, but the key consequences are disclosed.

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?

All four sentences carry distinct information: function, trigger phrases, downstream dependency, and subscription gate with fallback. It is a bit dense, especially the parenthetical trial/payment clause, but it is still efficient relative to the complexity. Front-loaded with the core start/stop behavior before commercial details.

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 3-parameter tool with no output schema, the description covers the main requirements: correct triggering, subscription prerequisite, fallback to get_sample_audit, and the relationship to get_changes. It doesn't describe return values or edge cases like duplicate domains, but those are not strongly needed given the schema and annotations. The description is sufficient for an agent to select and invoke the tool 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 description coverage is 100%: domain, cadence, and enabled all have descriptions, defaults, and enum constraints in the schema. The description only reinforces the cadence indirectly with 'on a schedule' and the enabled=false stopping behavior is already in the schema. Since the schema does the heavy lifting, this is a baseline 3.

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 description opens with 'Start (or stop) ongoing monitoring of a website's AI visibility on a schedule,' which names a specific verb and resource. It explicitly contrasts with a 'one-off check' and names get_changes as a downstream consumer, distinguishing it from siblings like run_audit and get_changes. This is far more specific than the title alone.

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 explicit trigger phrases ('monitor,' 'track,' 'watch,' 'get alerted about') and excludes one-off checks. It also provides a conditional alternative: if the user lacks a Website Auditor subscription, call get_sample_audit first. This is clear when-to-use and alternative routing.

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