cs_agent_send

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

The description adds valuable behavioral context beyond annotations: it explains that the idempotency key makes retries safe, revealing a key operational behavior. It also implicitly communicates async behavior by referencing cs_agent_wait_many. The annotations already provide readOnly, openWorld, idempotent, and destructive hints, so the description adds complementary operational context rather than contradicting them.

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 three sentences, each serving a clear purpose: what the tool does, what to include and why, and when to use it in parallel workflows. It is front-loaded with the primary action, contains no filler, and is appropriately sized for the tool's complexity.

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?

The description covers the core task, content requirements, idempotency, and parallel usage. It does not explicitly state how to retrieve the result for a single send, but the reference to cs_agent_wait_many and the availability of sibling wait tools provide sufficient context. Given the tool's complexity and lack of output schema, this is nearly complete, though a direct pointer to the wait step would have been ideal.

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 baseline is 3. The description goes further by explaining what should go into the 'content' parameter (objective, scope, constraints, expected deliverable, verification criteria) and clarifying the purpose of the idempotencyKey for safe retries. This adds practical meaning beyond the schema's per-parameter descriptions.

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 the verb 'Assign' with a specific resource ('managed descendant agent') and a concrete action (send a self-contained task). It distinguishes the tool from siblings like cs_agent_cancel, cs_agent_destroy, and cs_agent_get_message by focusing on task delegation. The instruction to include objective, scope, constraints, deliverable, and verification criteria further clarifies the purpose.

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 gives explicit guidance for parallel work: 'send all independent turns before waiting with cs_agent_wait_many,' which clearly indicates when to use this tool in a parallel workflow. It lacks an explicit 'when-not-to-use' or mention of alternatives for single-task waiting, but the context is sufficiently clear.

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