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

Annotations declare readOnlyHint=false and openWorldHint=true, so the description is not contradicting. It adds behavioral context beyond annotations: the tool returns an upload URL and requires external byte transfer ('outside model-authored tool arguments'), which is crucial for an agent to understand side effects. It also ties the prerequisites to the workflow, which is useful. Minor gap: it doesn't state whether the token expires or what happens on failure, but the core behavior is disclosed.

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 sentences, each earning its place: prerequisite, output, transfer method, and security note. No filler or redundancy. Information is front-loaded with the most critical constraint first. Highly efficient.

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 preparation tool with no output schema, the description covers prerequisites (rights and retention), the output (Supabase upload URL), the required transfer method (ZIP bytes via file-capable client), and a security caution (keep token private). The next step (finalize_review_upload) is a sibling and doesn't need to be described here. An agent has everything needed to invoke this correctly.

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 must compensate. It does not explicitly map the two boolean parameters (rights_to_submit, retention_accepted) but the phrase 'Only after the user confirms rights to submit and accepts the retention terms' strongly implies these are the confirmations. The parameter names are self-explanatory, and the description adds workflow context but no direct syntax or validation rules. This is adequate but not comprehensive.

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?

The description clearly states the tool's purpose: preparing a private project archive upload by returning a direct Supabase upload URL. It is a specific verb+resource and distinguishes itself from the sibling finalize_review_upload by framing this as the preparation step. The phrase 'Only after the user confirms...' anchors it in the workflow, making it unambiguous.

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?

Explicit when-to-use guidance: 'Only after the user confirms rights to submit and accepts the retention terms from get_review_requirements.' It also gives a negative instruction ('never base64 or paste code here') and a security directive ('Keep the upload token private'). The alternative workflow (finalize) is implied through the sibling list but not explicitly named; still, the conditions for calling are fully specified.

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