Submit Agent Task

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

The description adds meaningful behavioral context beyond the annotations: outputs are validated transactionally before anything is written, the execution epoch must come from a successful claim, stale epochs are rejected, and the document is resumed. This is strong for a write tool even though the annotations do not signal danger or contradiction.

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?

The description is compact, front-loaded with the core purpose, and organized with 'USE WHEN', 'NOT FOR', and 'ARGS' sections. Every sentence contributes actionable guidance with no wasted words.

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 tool with no output schema, the description covers the core workflow context: eligibility, arguments, validation behavior, contract enforcement, and resume semantics. It stops short of describing the response or potential failure modes after submission, but the key operational context is present.

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?

The input schema already documents all four parameters, so the baseline is 3. The description adds semantically valuable guidance by clarifying that outputs must be keyed exactly by the declared field key, that the optional summary is allowed, and that execution_epoch comes from a successful claim, which enriches the schema-only understanding.

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 a specific verb ('Submit') and resource ('declared output fields for a claimed Agent-stage task') and explains the resulting effect ('resume the parked document'). It also explicitly distinguishes itself from the sibling tool talonic_heartbeat_agent_task via the 'NOT FOR' clause.

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?

The description provides explicit 'USE WHEN' and 'NOT FOR' guidance, stating this tool is appropriate when processing is complete and every required output is ready, and inappropriate for undeclared fields or partial maintenance. It even names the alternative tool, making the boundaries unambiguous.

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