audit_parliamentary_speech

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

With no annotations, the description carries the full burden and exceeds it. It details the BERTimbau-based classifier, outputs (classification, confidence, entropy), the entropy threshold of >0.60, and how it triggers requires_human_review. This gives the agent a complete behavioral model of what the tool does and what to expect.

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 well-structured with an opening summary, usage guidance, bullet-pointed behavior details, and clear Args/Returns sections. While moderately long, each sentence provides necessary context; it is front-loaded and scannable without fluff.

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 the tool's analytical complexity and the presence of an output schema, the description adequately explains return fields (classification, confidence, entropy_uncertainty, class_probabilities, requires_human_review) and the decision logic. It also covers a broad range of use cases, making it complete for an agent to select and invoke 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?

The schema only defines 'text' as a string with no description. The tool description compensates fully by specifying 'Raw Portuguese utterance or transcript excerpt to audit', clarifying language and content expectations beyond the schema. Coverage gap of 0% is effectively closed.

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 the tool audits Portuguese parliamentary or political speech for offensive content, with a specific verb 'audit' and resource. It elaborates on scope including floor speeches, committee interventions, social media posts, and campaign rhetoric, making the purpose unambiguous even without 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?

Explicitly instructs 'Use this tool whenever a user asks you to analyse, moderate, classify, or safety-check political / legislative discourse in Portuguese (PT-BR)', providing concrete triggers for use. It effectively communicates when to apply the tool, even without listing alternatives.

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