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

The description goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=true, destructiveHint=false). It discloses that the report is deterministic with 'no LLM in the grounded path' (cannot invent statutes), that every obligation is anchored to real law, and that it is informational only, not legal advice. It also explains tier-specific behavior (preview vs. full report). There is no contradiction with annotations.

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, coherent paragraph of about seven sentences. It front-loads the primary purpose and includes critical disclaimers (no LLM, not legal advice) and tier behavior. While it is not excessively long, it could be more structured (e.g., bullet points for tiers) to improve scanability. It earns its sentences, but minor structural improvements would boost usability.

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 complexity (12 parameters, no output schema, tiered access), the description covers all essential behavioral aspects: return values (risk score + download URL), tier limitations, deterministic nature, legal grounding, and disclaimers. It provides sufficient context for an agent to correctly invoke the tool and interpret results. The absence of an output schema is compensated by explicit description of the output contents.

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 67%, but the description adds value by explicitly naming `state` and `sector` as required and noting that `jurisdiction` is an alias for `state`. This provides clarity beyond the schema, which already marks them required. However, the description does not detail other parameters like `ai_policy` or `bias_audit`, so it doesn't fully compensate for missing schema descriptions. The alias information earns a 4.

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 generates a 'personalized, source-grounded AI-law COMPLIANCE REPORT' for a business profile. It distinguishes itself from sibling tools by noting it is the same deterministic engine behind the $79 report product and that it returns a risk assessment and download URL. This specificity meets the 'specific verb+resource' criterion and differentiates it from other list/get tools.

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 provides clear context on when to use the tool (for generating a comprehensive compliance report) and includes important caveats: it is a paid feature (Pro+), and lower tiers only get a preview. While it doesn't explicitly state when not to use it or name alternative siblings, it implies the tool's purpose versus component tools like get_ai_obligations. This is clear but lacks explicit exclusion guidance.

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