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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description still adds genuine behavioral context: templates are guaranteed to pass the preflight email check for their kind, and in check mode merge fields are filled from the site's plan before the check runs across the site's jurisdictions. It does not say what a failing check returns, but with no output schema that is a modest gap.

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?

Three tight sentences, front-loaded with what you get, then the two parameter modes in the order an agent would consider them. No filler; the density in 'each passing the preflight email check for its kind' is slightly compressed but still parseable.

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 read-only, two-parameter tool with a nested check object and no output schema, the description covers both modes, the merge-field substitution behavior, and the multi-jurisdiction checking scope. Missing only the result shape of a failed check, which is a secondary concern given the read-only, idempotent annotations.

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 coverage is 100%, so the baseline would be 3. The description goes beyond the schema by explaining the effect of each parameter: site yields BCC addresses per kind, and check triggers merge-field population from the site's plan plus a multi-jurisdiction preflight pass — semantics the schema's terse field descriptions do not convey.

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 (get notice templates) and immediately qualifies the content: copy-ready HTML + text with {{merge_fields}} for every required email, all preflight-validated. The description also names the dual mode (list Checkbox's templates vs. check the merchant's own), which distinguishes it from siblings like check_email or get_notice_schedule.

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?

Explicitly states the two invocation modes and the condition for each: 'Pass site to get the BCC address per kind' and 'Pass check ... to check the merchant's own version instead.' The 'instead' wording makes the modes mutually exclusive. It does not mention when to use the sibling check_email instead, which is the one remaining routing gap.

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