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

The annotations already declare a mutating, non-idempotent, non-destructive, open-world operation, so the safety profile is carried. Beyond that the description adds the upload_media dependency chain, which is genuinely useful, but says nothing about failure on duplicate names, required permissions, or exit state. The image-format constraint (no SVG) also lives in the schema, so it is not new behavioral disclosure.

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 short sentences with no filler, and the site scoping and prerequisite are front-loaded. The elliptical fragment style ("On one site of the account, named in site. A new badge:") costs a little immediate scannability compared with plain declarative phrasing.

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 four-parameter creation tool with full schema coverage and no output schema, the definition covers the essential call path: scope, the fields to supply, the media prerequisite, and the follow-up tool. Only edge-case behavior — duplicate-name rejection, permissions, what a successful call returns — is left unstated.

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 is 3: the schema already defines the 60-character case-insensitive uniqueness of name, the site naming convention, and the upload_media-produced url. The description's "a line saying what it is for" and "a picture" restate the description and image_url semantics rather than extending them, though the upload-first ordering does add procedural meaning.

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?

"A new badge" on "one site of the account, named in site" with a name, a purpose line and a picture makes the created resource and its components unmistakable, and it is clearly distinguished from update_badge, list_badges and award_badge. It stops short of a clean verb-first statement — the opening is a sentence fragment — so it is clear rather than exemplary.

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?

It states the prerequisite sequence explicitly: upload the file with upload_media first and pass the returned url, then hand the badge out later with award_badge. That routes the agent correctly within the badge workflow. It gives no exclusion versus update_badge or guidance on what to do when a badge of that name already exists.

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