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

Without this description, the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) would leave behavior opaque. The description fills the gap richly: it explains the admission check, the refusal reasons (seat_not_yours, not_routable), the 404-vs-403 security policy, the required permission (agent:dispatch:code), and the fact that it does not itself mint a receipt. This is exactly the context annotations cannot carry.

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 dense but well-structured, with the core claim operation and admission rule front-loaded, followed by refusal semantics and permission requirements. Every clause carries specific information. It is slightly long for a tool definition, but the density is justified by the non-obvious behavior being explained.

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?

Given the tool's complexity—a state-mutating claim operation with strict identity and routing rules—the description covers entry criteria, failure modes, permissions, and the relationship to subsequent tools. No output schema exists, but the description clarifies that the tool 'opens the run' and that receipts come later, which is sufficient context for invocation.

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 description coverage is 100%, so the schema already documents each parameter clearly (agent_id prefix rule for 'instance', TTL range for 'ttl_seconds', source of task_id). The description reinforces the instance requirement but adds no syntax or format details beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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 opens with a specific verb+resource ('Claim a fan-out seat task as a LOCAL subagent run') and immediately names the mechanism and sibling relationship ('POST /runs/claim -> claim_agent_run(p_runner='local')'). It distinguishes itself from adjacent tools like tascan_create_fanout and tascan_finish_run by describing exactly which phase of the workflow it occupies.

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?

Explicit conditions for invocation are given: only admitted when the instance prefix matches the seat's coord.agent_id, never for cloud (research) seats. It also directs the reader to tascan_heartbeat_run for extending leases and tascan_finish_run for completion, so the agent knows what to use instead.

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