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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description goes well beyond that by disclosing caching (7 days), pure compute (no external fetch), input size expectations (10k–100k chars), auto-detection of doc type/language, and output granularity (16+ clause types, risk detectors, deadline calendar). This adds substantial behavioral context beyond the structured 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 longer than average but well-organized: a clear opening sentence, a lead paragraph on purpose, followed by bullet-point capabilities and a purity note. Every line earns its place with concrete technical detail (e.g., 20 obligation patterns, P0/P1/P2 severity). It is dense yet scannable, so it earns a 4 rather than a 5 only because it could be tightened slightly without losing value.

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 (5 parameters, output schema, many capabilities), the description is comprehensive. It covers input constraints, output features, caching, compute semantics, and targeted users. The presence of an output schema means return details are not required, and the description fills all contextual gaps (auto-detection, cache, pure compute, doc types).

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 coverage is 100% with detailed param descriptions (lang, async, document_text, document_type, target_clauses). The tool description adds only minor param-related context, such as typical document size (10k–100k chars) and supported languages, but mostly repeats what the schema already explains. It does not significantly enhance parameter understanding beyond the structured fields.

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 verb+resource: 'Structured extraction of clauses, obligations and deadlines from legal documents'. It lists concrete document types (SaaS contracts, NDAs, employment agreements, etc.) and explicitly distinguishes itself from sibling contract_risk_scanner by offering 'granular per-clause output'.

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: it names contract_risk_scanner as a complementary alternative and identifies target users (legal ops, M&A lawyers, etc.). However, it does not explicitly state when not to use this tool or give exclusions/alternatives beyond the one sibling mention.

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