gc_plan

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It fails to state whether actions mutate state (e.g., upsert_resource, upsert_profile likely write), whether next/replan consume or modify the queue, whether simulate is read-only, or whether solve_and_validate has side effects. It lists actions but gives no behavioral detail about effects, prerequisites, or side effects whatsoever.

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 short (two sentences), but the second sentence is a raw action-name dump that uses significant space to enumerate actions without explaining them. Every token could 'earn its place' with even a one-line gloss per action group. The opening 'Resource-constrained scheduler' and question are useful but the action list adds little value as written.

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?

This is a high-complexity tool: 19 parameters, 15 distinct actions, no output schema, and no annotations. The description fails to convey the state machine between actions (e.g., profile → resources → capacity → simulate → solve), which actions are required in sequence, what each action returns, or what inputs each action needs from the 19 available parameters. This is a significant completeness gap for a tool of this complexity.

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 all 19 parameters have descriptions in the schema, which sets the baseline at 3. The description itself adds zero parameter context. However, many parameter descriptions reference named entities (e.g., 'Leonidas' default resource, scenario names like 'revenue_mode') that are opaque without further explanation, and the description does nothing to clarify these domain-specific values.

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 says 'Resource-constrained scheduler' and poses a guiding question ('What should I work on next?'), which establishes the general domain. However, it does not use a specific verb+resource structure for this single tool, and it lists 15 potential actions without explaining what each does. The purpose is understandable at the domain level but opaque at the operation level; an agent cannot tell what outcome to expect from any individual action without deeper inspection of the schema.

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?

There is no guidance on when to use this tool vs. alternatives, nor when NOT to use it. The sibling tools include gc_schedule and gc_work, which could plausibly overlap with scheduling/replanning, yet no differentiation is offered. The description simply lists available actions without context on which to pick or when the tool is appropriate.

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