Check a push, SMS, in-app, content card or webhook

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this consistently with 'Read-only; sends nothing'. Beyond that it discloses substantive behavior the annotations cannot: personalization is rendered against synthetic personas, and specific check categories (lock-screen/segment limits, SMS encoding and billed segments, link host validation, secret-in-URL detection) are performed. What is missing is any hint of the output shape or whether checks can fail hard.

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 verb and resource, and every clause names a concrete check rather than restating the title. The single long sentence is dense but readable; it could be split into 'what it does' and 'what it checks' for faster scanning.

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 11 parameters, no output schema and no nested objects, the definition does enough to let an agent assemble a correct call and understand what will be validated. The residual gap is return values: absent an output schema, the description should say whether the agent receives a findings list, pass/fail verdicts, or rendered previews.

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 64%, so the schema carries much of the burden, and the description adds real meaning for personas (rendering synthetic attribute sets), buttons, deep_link, webhook_url and quoted-string breakage in JSON bodies. However it never explains that 'platform' selects the template language whose syntax will be rendered, and 'name', 'image_url' and 'webhook_method' go unmentioned despite 11 parameters. The platform omission is the most costly gap.

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 ('QA one push notification, SMS/MMS, in-app message, content card or webhook') and enumerates the exact channel scope, which immediately separates it from check_email and check_campaign. It also names the rule source ('the team's house rules'), telling the agent which governance framework is applied.

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 by the channel list and by the sibling set (check_email, check_campaign), but the description never explicitly says 'use this instead of X when Y' nor states prerequisites such as 'platform must match the template language used in the body'. The 'Read-only; sends nothing' line gives useful framing but not routing guidance.

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