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

Annotations only declare the generic safety profile (readOnly=false, idempotent=false, destructive=false, openWorld=true). The description goes well beyond: a 50-page cap, the intervalMinutes range of 5-10,080, per-check billing ('Each check bills the pages it fetches'), and an authentication requirement ('Needs a free SnoopScan key') — cost and auth details an agent cannot get from structured fields.

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 the core action and limit, followed by the interval range, billing, and sibling routing in tight sentences. The trailing 'Needs a free SnoopScan key.' reads as a dangling fragment rather than a structured prerequisite, but every sentence carries information.

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?

An output schema exists, so return values need no explanation, and the description covers scheduling, limits, cost, auth, and follow-up tools. The only real gap is the unexplained 'goal' parameter and no stated behavior for what happens on failure or how monitors are managed/deleted.

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 0% across 4 parameters, so the description must compensate. It does add real value for intervalMinutes (valid range 5-10,080 vs. the schema's bare default of 60) and indirectly caps urls at 50, but name and goal are never explained — notably 'goal' is a non-obvious parameter left entirely undefined.

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 ('Start a monitor that re-reads up to 50 pages on a schedule') plus the outcome ('records which are new, changed or failing'). It also names the sibling tools checkMonitor and listMonitors, so an agent can separate creating a monitor from reading or listing one.

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 clear routing: read the latest result with checkMonitor, list yours with listMonitors. It establishes context for the create/monitor workflow but never states when a monitor is preferable to one-off siblings like scrape or crawl, nor any exclusion conditions.

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