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

The line 'A person reviews every report before any list changes' is genuinely additive: it discloses human moderation, that the effect is deferred, and that the call itself does not mutate the classification list. This complements the non-readOnly/non-destructive/idempotent=false annotations rather than repeating them. It still omits what the call returns or whether submitter identity auth is required.

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?

Two tight sentences, front-loaded with the action and followed by the one behavioral fact that matters. No filler and nothing that merely restates the title.

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 3-parameter mutation tool with no output schema and thin schema descriptions, the description covers the key behavioral risk (human review) but leaves parameter usage and expected response shape unexplained. Adequate to call correctly, but the low schema coverage leaves visible gaps.

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 only 33%, so the description must carry more of the burden. It does clarify the 'input' parameter as 'an address or domain', but says nothing about 'expected_category' (which drives the whole report) or the optional 'comment', leaving the enum of seven categories and the comment's purpose/limit unexplained in prose.

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 names a specific verb+resource: submitting a correction report to isBusinessEmail about a wrongly classified address or domain. This clearly separates it from the sibling check_* tools, which query classifications rather than dispute them. It stops short of naming those siblings as the pre-requisite path, but the action is unambiguous.

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 only implied: an agent infers it should call this after check_email/check_domain returns a classification it believes is wrong. There is no explicit when-to-use condition, no statement about whether a prior check is required, and no note on duplicate or repeated reports.

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