Record a need when an agent is blocked

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

Far beyond the annotations, it discloses that a human does the routing, that no delay is promised, that each call creates a non-retried record (consistent with idempotentHint=false), that sensitive values are masked with warnings naming masked fields, and that the first call sets is_authenticated. These are exactly the side-effect details an agent needs before invoking a write tool.

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 is front-loaded in the first sentence, with operational caveats following in a compact sequence. Density is high but nearly every clause carries non-obvious information; only the is_authenticated side effect feels appended rather than integrated.

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 write tool with no output schema, it covers routing, safety, retry behavior, and next steps. The one residual gap is what the call returns (a record identifier?) that get_handoff_status would consume, which the agent must infer.

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 the baseline is 3, but the description adds a genuine parameter-usage rule not present in the schema: never put keys or client data into the free-text field because detection and masking will occur. It adds nothing for deadline or acceptance_criteria, which the schema already constrains fully.

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 states a specific verb and resource ("Records what the agent could not do") and explicitly corrects the misleading tool name by saying "no specialist is returned by this call." It also distinguishes itself from the sibling get_handoff_status by framing that call as the follow-up step.

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?

It gives clear sequencing guidance ("Follow the need with get_handoff_status") and manages expectations about human routing and delay. It stops short of stating when an agent should NOT file a need, but the operating context is clear enough to act on.

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