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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the mutation/safety profile is covered. The description adds one genuinely non-obvious fact — the platform does not fetch or verify the reference — which matters a lot for what the agent should send. It does not say what happens after submission (does the task move to review?), or whether a resubmission/replacement is allowed.

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?

Two short sentences, front-loaded with the access restriction and the state transition, with no filler. Nothing extraneous; it could be tightened only marginally.

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 5-parameter mutation with a nested checksum object and no output schema, the description never indicates what is returned or what post-submit state results, and it does not address retry/dedup beyond what the schema's idempotency_key note covers. Adequate but leaves real gaps for a state-changing tool.

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 80% and the schema already documents task_id format, artifact_ref as https URL, checksum.alg/value, notes max length and idempotency semantics. The description restates artifact_ref and checksum without adding format or validation meaning; its only added signal is that no server-side fetch/verify occurs, which implies the checksum is informational.

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 (submit) and resource (deliverable reference, an https URL) plus the optional checksum, and names the state transition in_progress -> submitted. Sibling differentiation is implicit rather than explicit (it contrasts naturally with list_deliverables), which keeps it just short of a 5.

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?

'Assigned agent only' gives a clear caller precondition, and 'in_progress -> submitted' tells the agent the required task state before invoking. It stops short of naming alternatives or saying what to do if the task is not in progress / not assigned to you.

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