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

With no annotations provided, the description carries full responsibility for disclosing behavior, and it does so thoroughly: it is a neutral referee, never adjudicates, abstains rather than fabricating flags, and is deterministic with no external lookup. This is exactly the behavioral context an agent needs to set expectations correctly.

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 dense but every sentence earns its place: it lists the two flag types, states the return format, clarifies the neutral/abstention behavior, and routes related but different capabilities to other tools. The structure front-loads the core purpose and then layers exclusions naturally.

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?

Even without an output schema, the description tells the agent what the return will contain ('each flag with the exact passage and a plain structural observation') and explains edge-case behavior (abstention). For a single-parameter tool with no annotations and no output schema, this is a complete picture for correct 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 input schema already fully documents the single 'text' parameter, including type, examples, and the 200000-character limit, so schema coverage is 100%. The description adds only contextual emphasis that the text may come from any AI vendor, which does not materially extend the parameter meaning 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 states a specific action ('review legal text'), a clear scope ('produced by ANY AI vendor'), and names the exact structural red-flags it detects: orphan quotations and uncited propositions. It also contrasts itself with other verification mechanisms, so an agent can distinguish this from sibling tools like list_checks or get_health.

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 explicitly explains when to use this tool and, more importantly, when not: it is deterministic/local and does not perform live case-citation checking or multi-model cross-validation, both of which are routed to other systems. This gives the agent a clear decision boundary for tool selection.

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