tcai_metrics

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

With no annotations, the description must carry the full burden of disclosing behavior. It only provides a nominal label and metric list, without stating whether this is a read-only report, what side effects exist, or what the output looks like. This is a significant transparency gap.

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 extremely concise, a single fragment that efficiently lists the report type and key metrics. It is not verbose and every word adds information, though it is structurally a fragment rather than a complete sentence.

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 has no output schema and no parameters, so the description is the only source of information. It names the metrics but doesn't explain what 'composite score' means, how the report is presented, or how to interpret the values. This is a notable gap for a report tool.

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 tool has zero parameters, so the schema is fully covered by default. There are no parameter semantics to describe, and the baseline of 4 applies because the description doesn't need to compensate for missing parameter documentation.

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 identifies the tool as a 'Consciousness proxy report' and names specific metrics, which gives it some clarity. However, it lacks an explicit verb like 'get' or 'generate', making the action somewhat implied. It does distinguish from siblings by naming unique metrics like GNW and Φ̃-RIIU, but only partially.

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 such as tcai_self_model or get_metrics. No usage context, when/when-not conditions, or alternative references are provided, leaving the agent to guess.

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