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

Annotations already declare readOnly=false, idempotent=true, destructive=false, but the description adds what the annotations cannot: an exact byte-preservation guarantee, the 2 MiB remote-request ceiling (including base64 encoding overhead), the 100 MiB alternative path, and the mandatory idempotency key. These are exactly the constraints an agent must respect before calling.

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 tight sentences with the core guarantee front-loaded and constraints following. The 'Base64 input.' fragment is terse but earns its place by flagging the encoding contract; nothing else is wasted.

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 write tool with annotations covering safety and no output schema, the description supplies the size limits, encoding requirement, and idempotency contract that structured fields omit. It stops short of indicating the natural next step (confirm_artifact_submission) or what a successful store returns, but nothing critical for invocation is missing.

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 0%, so the description carries the parameter burden. It explains that input is base64 and that the idempotency key is required, which is real added meaning, but it never clarifies the 'path' field or the files-array semantics (up to 1024 entries, exact bytes per path). Baseline 3 given partial compensation for a coverage 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+resource+timing: 'Store authenticated exact file bytes before a submission transaction.' That cleanly separates it from read siblings (get_verification_artifact) and from prepare_artifact_submission/confirm_artifact_submission, which handle the submission lifecycle rather than byte storage.

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 explicit preconditions ('before a submission transaction') and names the fallbacks for cases it cannot serve: larger files go through the API/CLI (100 MiB total) or exact GitHub commit import. An agent knows both when to pick this tool and when to route elsewhere.

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