coeus_thinkdeep

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

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Structured deep investigation' vaguely suggests a multi-step or resource-intensive process, but it does not state what happens, what the output looks like, whether it has side effects, or what inputs are essential. This is insufficient transparency for a tool with no annotation support.

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 a single, efficient sentence with no filler and is front-loaded with the action verb. It earns high marks for conciseness, though it is arguably too terse to serve as a complete definition for a tool with five parameters.

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 tool with 5 parameters, no output schema, and no annotations, the description is completely inadequate. It provides only a one-line purpose and omits essential context such as when to use it, what each parameter does, expected results, or edge behavior. An agent cannot reliably select and invoke this tool based on the provided information.

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?

Although the schema describes all parameters (100% coverage), those descriptions are merely the parameter names repeated ('Model', 'Context', etc.), adding no semantic value. The tool description itself mentions 'bug, decision, or risk' which loosely maps to 'problem', but it does not explain model, context, constraints, or focus_areas, nor their relation to the investigation. The description does not compensate for the schema's low-usability parameter metadata.

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 a verb ('run') and a resource ('structured deep investigation') with targets ('bug, decision, or risk'), making the basic purpose understandable. However, it does not differentiate this from several similar sibling tools (e.g., coeus_analyze, coeus_critical_debate, coeus_second_opinion), so it does not meet the full bar of distinguishing from siblings.

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 versus alternatives, nor any mention of preconditions or exclusions. The description is purely definitional and leaves the agent to guess which of the many analysis-oriented sibling tools fits a given situation.

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