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

Annotations only say this is a non-read-only, open-world, idempotent, non-destructive call; the description adds the crucial missing context: exact price (EUR 2 / USD 2, ex-tax), that it is a paid MPP charge requiring the payments:publication-check scope and validated billing, that nothing destructive happens but publication is not triggered, and a security warning not to pass payment credentials.

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 purpose and cost, and every sentence carries information (prerequisites, sequencing, credential warning). Some clauses are dense run-ons (the pricing/scope sentence), but there is little 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 paid, 10-parameter, 8-required tool with no output schema and no sibling name, the description covers pricing, auth/scopes, billing validation, the awaiting_publication hand-off, and the non-regression caveat about unlisted fields. What remains thin is the form of the result and the role of the idempotency/confirmation parameters.

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 10 parameters (8 required, nested object), so the description carries the load. It meaningfully explains the `expected` object (exact desired values for the AFTER capture) and ties the price/locale/currency and the four confirmation booleans to billing and authority requirements, but leaves idempotency_key and several individual confirmation flags unaddressed.

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 gives a specific verb+resource+scope: 'Capture a paid BEFORE-publication baseline for one public HTML page.' It implicitly distinguishes itself from the AFTER/comparison step ('includes one comparison within 7 days', 'exact desired values for the AFTER capture'), but never names the sibling it is not (e.g. kanonyr_compare_publication), so an agent must infer the boundary.

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 clearly frames this as the BEFORE step ('Wait for awaiting_publication before the client changes the site') and rules out alternatives ('No credits, subscription or automatic publication'), plus lists the scope and billing prerequisites. It does not explicitly state when to call the sibling comparison tool instead, leaving one inference to the agent.

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