task_submit

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered structurally. The description adds genuine behavioral context (exclusive tree leases, repair limits, verification commands that task_verify runs), but omits what happens on duplicate submission, whether tasks can be cancelled/reconciled, and the durability/persistence semantics implied by 'durable'.

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 sentences, front-loaded with the core action, no filler. Efficient, though the second sentence is a compressed feature dump rather than structured guidance.

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 15-parameter mutation tool with no output schema and only 27% schema coverage, the description leaves major gaps: what the returned task identifier is, how this relates to task_claim/task_ready/task_verify, and how the many optional contract parameters interact. It is insufficiently complete for correct invocation without reading the schema.

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 only 27% for 15 parameters, so the description must compensate and it does so only loosely: it gestures at dependencies, leases, idempotency, repair limits, and verification commands without mapping them to parameter names or formats. Required fields cwd and objective, plus acceptance, metadata, priority and requireIndependentVerifier, get no elaboration.

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: 'Create a durable provider-neutral agent task.' An agent can distinguish this as the submission/creation tool within the task_* family. It does not, however, explicitly contrast itself with siblings like task_claim or task_next, so it falls 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?

There is no when-to-use guidance, no prerequisites (e.g., an active lease/workspace), and no named alternative. The feature list ('Supports dependencies, exclusive tree leases...') describes capabilities, not selection criteria, so the agent must infer that this is the entry point for the task lifecycle.

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