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

Annotations only say readOnlyHint=false and openWorldHint=true; the description goes much further, disclosing that nothing is watched until the recipient opens the link, that they can stop any time, that emails are short and only on days the record changes, and the 25-listing ceiling. This is exactly the extra context annotations cannot carry.

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?

The core action and limit are front-loaded in the first sentence, and the quoted consent block is long but deliberately verbatim so it can be shown to the user. Some middle clauses (status, workers' comp, bonds, classes, expiry) repeat twice, which slightly bloats an otherwise purposeful description.

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 consent-gated, externally-emailing tool, the description covers eligibility, the consent workflow, the 25-listing cap, and the lifecycle of the watch. An output schema exists, so return values need not be explained here, and nothing an agent needs to call it correctly is missing.

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%, so email, slugs, and consent are already documented, including maxItems of 25. The description reinforces the consent semantics and the person's-own-email rule, but adds little syntax or meaning not already in the schema. Baseline 3 applies.

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?

First sentence gives a specific verb and resource: it emails a person a link so they can watch up to 25 listings free, and it names the eligibility constraint (CSLB contractors only). The scope is clear enough to tell apart from read-only siblings like get_business, though it never explicitly differentiates itself from the sibling watch_licenses.

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?

Explicit preconditions: use the person's own email, only when they asked, and show them the quoted consent sentence and get a yes before calling. That is strong when-to-use guidance. It stops short of naming alternatives (e.g., watch_licenses) or saying when not to use it.

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