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

Annotations declare readOnlyHint=false and openWorldHint=true, which could make an agent hesitate, and the description resolves exactly that: it explains an email is sent to the supplied address, a Levered marketer reviews and replies, but nothing is charged, no form is submitted, and nothing changes on the site. It also discloses the shape of the response (what was checked, top three problems, first task) even though no output schema exists. That is substantive behavioral context beyond the annotation block.

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 purpose and required inputs are front-loaded, and the safety disclosure is placed at the end where it answers the obvious follow-up concern. The middle enumeration of checks is dense and slightly list-like inside prose, but each item informs what the report covers, so little is wasted.

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?

With no output schema, the description must explain the return value, and it does: text written for a person, containing what was checked, the top three problems, the first task Levered would do, and how to start. Combined with the side-effect disclosures for a non-read-only, open-world tool, an agent has everything needed to call it and set expectations 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 coverage is 100%, so the schema already documents all three parameters, including format examples and the 'use the address the person gave you' note. The description reinforces the meaning of email as the delivery destination but adds nothing about business_name and no new syntax beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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 ('Website check from Levered') and immediately enumerates the scope: site and competitors, tracking/conversion tags, Google and Meta ads from public libraries, ad-to-conversion paths, SEO and AI-search visibility. This is far more specific than the sibling names about_levered and how_to_connect, which are informational, so an agent can distinguish them without opening either schema.

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?

Usage is implied rather than stated: the tool takes a business website and an email, which signals 'use when someone wants an external audit of a site'. There is no explicit when-to-use/when-not framing and no mention of the sibling tools or a condition that would route an agent to them instead. The 'no sign-in' and 'Nothing is charged' lines help the agent decide it is safe to call, but they are not selection guidance.

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