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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds behavior beyond that: multiple codes are returned joined by newlines, and no API key/account/signup is required. It omits rate limits and what happens when no code is found, so not a 5.

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?

Four short sentences, front-loaded with purpose and formats, then return behavior, input choice, and auth note. Nothing is padded and every sentence carries distinct information.

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 usefully explains the newline-joined return format and covers accepted formats, input paths, and auth. It lacks error/empty-result behavior and any rate or size context beyond what the schema already states.

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 the baseline is 3; the schema already documents storage_id provenance, 24h expiry, and the base64 size limit. The description's "or" only clarifies that the two parameters are mutually alternative input paths, a marginal addition over the schema.

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 (read) and resource (QR codes) plus the accepted image formats (PNG, JPEG, GIF, WebP), which cleanly separates it from the sibling create_qr_code. An agent can tell what it does and what it accepts without opening the 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?

"Give image_base64 or storage_id" tells the caller how to supply input, which is real usage guidance, but there is no when-to-use/when-not context and no comparison to neighbors like process_image or read_stored_file. Usage is implied rather than framed.

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