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

Goes well beyond the annotations: the uploadId expires after 2 hours, the 200-file and plan-dependent size limits, and the important nuance that starting is non-destructive while publishing replaces the site's files — consistent with destructiveHint=false but explaining why. That resolves the one place an agent could misjudge risk from the annotations alone.

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?

Purpose and the uploadId return are front-loaded, and every sentence carries information. The limits sentence is dense, packing file count, two plan tiers and a pointer to the result's limits into one clause, which costs a little readability.

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?

No output schema exists, and the description covers the return value (uploadId), its lifetime, the size constraints an agent must respect before uploading, and the create-vs-replace semantics. That is everything needed to call it correctly and plan the follow-up steps.

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 baseline is 3, but the description adds the consequence of each branch — siteId means publishing overwrites that site, its absence means name/subdomain define a new site — which is more than the terse schema text. The message parameter's role in deployment history is left entirely to 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 ('Starts a deploy whose files are sent in several parts') and scopes it to sites too large for a single call. It also rules out a misreading with 'is not a deploy' and 'changes nothing live', which separates it conceptually from deploy_site. It stops short of naming the sibling tools it hands off to, so sibling differentiation is implied rather than explicit.

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 clear selection condition ('a site too large to send in one call') and a full branch on siteId: replace an existing site vs. create a new one with name/subdomain. What is missing is an explicit negative case and hand-off naming — nothing says to use deploy_site for small sites or that upload_files/publish_upload complete the flow.

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