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

Annotations already declare idempotentHint=true, destructiveHint=false and readOnly=false, so safey/write semantics are covered. The description adds genuinely useful context beyond them: byte-level validation and deduplication against face-source/publication rules, and that it returns a pack plus a created flag. It does not describe what happens on a dedup hit in detail, keeping it below 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?

Front-loads the core action and keeps to five tight sentences, each carrying distinct information (scope, size limit, alternatives, validation, return). Slightly dense but no filler.

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 an output schema present, the brief mention of returned pack/created flag is sufficient, and annotations carry the safety profile. For a 4-required-param mutation the description covers scope, limits, and validation well; only the large-file alternative path is left unnamed.

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, but the description adds meaningful detail: canonical base64 without a data-URL prefix, the ~512 KiB decoded ceiling, and that MIME type is cross-checked against the bytes. This reinforces endpooint-specific constraints beyond the enum and pattern already in 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 and resource ("Adds a customer photograph to Artist DNA") and immediately scopes it as an existing photo, not generation. "No image generation" plus the sibling reference-add/upload-path naming lets an agent distinguish it from generation and media-upload tools 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?

Gives a concrete routing threshold: inline input is for files up to 512 KiB, while "larger files have dedicated upload/app paths." That is clear conditional guidance, though it stops short of naming the specific alternative tool or stating exclusions beyond size.

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