tcai_capability_model

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

With no annotations, the description carries the full burden. It establishes read-only semantics via 'query' and 'list', and adds useful context about the underlying model (DirectExperienceLearner port, EMA). It does not detail edge cases or exact output format, but for a read-only lookup this is reasonably transparent.

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 sentence that is front-loaded with the essential purpose ('Agency capability model') and immediately explains the action-to-valence mapping. No wasted words.

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 tool is simple with only one optional parameter and no output schema. The description covers the two primary operations (query by action, list all) and the conceptual model. It could mention return value details or behavior for unknown actions, but overall it is sufficient for basic invocation.

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?

The schema already fully describes the 'action' parameter, so the baseline is 3. The description adds meaning by explaining that the parameter is optional and that omitting it triggers the list-table behavior ('or list the learned capability table'), which is not stated in the schema. This goes beyond the schema.

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 uses specific verbs ('query', 'list') and identifies the resource ('capability model', 'action → expected-valence map'). It clearly distinguishes this as a lookup tool for learned action-outcome associations and distinguishes it from siblings like tcai_meta_learning or tcai_second_order.

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 implies when to use the tool: to query an action's expected outcome or to list the capability table. However, it does not explicitly mention alternatives or provide exclusions relative to other tcai tools, so usage guidance is present but not fully explicit.

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