AgentStack

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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false; the description adds required auth via Connect/Device Code, project_id on every batch, CAS/leases, and async polling. It does not contradict annotations and adds meaningful operational constraints, though it omits some mutation impact details.

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 but packed with internal jargon and repeated spine/agent sequences, and it does not front-load the tool's own purpose. Some auth/prompt details are useful context, but the structure is hard to parse.

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 complex nested batch executor with an output schema and annotations, it supplies auth prerequisites, project_id scoping, work-loop routing, and async behavior. Missing a plain-language statement of the tool's core action keeps it from full completeness.

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 steps/context/options. The description adds only limited semantic guidance (project_id required, sync vs async, packet usage), so baseline 3 is appropriate.

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 frames the tool as the AgentStack work-graph control plane and names related planning/execution calls, but it never directly states that agentstack.execute runs a batch of catalog actions. The purpose is inferable from the tool name and schema, yet the description itself remains jargon-heavy and indirect.

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 prescribes an explicit sequence after session/project_id and says to follow packet.next_action, with discovery.search only when no packet and direct domain actions for one-shot CRM/upload. Alternatives are named, though the routing remains terse.

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