gc_posture

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

No annotations are provided, so the description carries the full transparency burden. It reveals nothing about side effects: whether set_global persists across sessions, whether clear_tool_trust is reversible, how levels (cautious/normal/trusting) affect downstream behavior, or any authorization requirements. The reference to 'Story 3.6' and 'FR-6' provides no useful behavioral disclosure.

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 and the action list is compact. However, the reference to 'Story 3.6, FR-6' is meaningless to an agent and wastes tokens. The line about actions is borderline useful as a scope indicator, but the overall structure doesn't earn its minimal length — there's one sentence of actual value.

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 this is a 4-parameter tool with enums and no output schema, the description should explain the semantics of acting on trust posture — but it doesn't. It doesn't describe what 'loosen_reasons' accomplishes, how levels map to behavior, what get returns, or how this interrelates with other gc_* capabilities. The specification reference suggests this is a niche internal tool that needs more context for an agent to use correctly.

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 parameters are documented in the input schema. The description adds minimal value beyond schema — it repeats which action maps to which parameter via parenthetical hints ('for set_tool_trust/clear_tool_trust'), which the schema already states. There's no added depth about value semantics or constraints, but 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 describes gc_posture as an 'Operator-tunable trust posture' and lists actions, but doesn't clearly state what the tool does as a verb+resource. 'Trust posture' is vague — it doesn't explain what a posture is, what changing it affects, or how it differs from the many sibling gc_* tools. The description reads more like a spec reference (Story 3.6, FR-6) than a functional explanation.

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?

No guidance on when to use this tool versus any sibling. The action list implies operations but gives no context about the decision flow — when would an operator get vs set trust, or what situations call for tool trust vs global posture changes. No exclusions or alternatives are mentioned.

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