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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description's restatement of 'Read-only. No side effects. Idempotent' adds no new safety info. However, it adds meaningful behavioral context not in annotations: automatic patent number normalization, a 24-hour cache, and the verified EPO OPS source. This goes beyond what structured fields convey, though it could have explained cache staleness or rate limits for an even higher score.

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 relatively long, but every sentence earns its place: purpose, read-only assurance, parameter details, return fields, usage alternative, source/cache, and feedback escalation. It is front-loaded with the core action. The only mild redundancy is repeating read-only/idempotent which annotations already provide, but this does not significantly detract.

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?

For a two-parameter tool with a full output schema and rich annotations, this description is remarkably complete. It covers exact input formatting, normalization behavior, a verified source, cache policy, return fields, and even a fallback feedback mechanism. No critical information an agent needs to call the tool correctly is missing.

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 100%, but the description adds substantial meaning beyond the schema: EPODOC format with concrete examples for EP, CN, JP, PCT, and US; the tropical interoperability of jurisdiction as a hint rather than a strict filter; and the auto-normalization behavior. This gives an agent the exact input format expectations and reduces the chance of malformed calls.

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 opens with a specific verb-resource pair: 'Fetch full patent details by patent number and jurisdiction.' It differentiates from siblings by explicitly naming legal_search_patents_by_keyword for keyword-based searches, and from legal_fetch_patent_citations/legal_fetch_inventor_portfolio by its focus on a single patent's full details. Also lists concrete return contents, so an agent can identify the tool's scope immediately.

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?

Provides explicit selection criteria: 'Use this when you have a specific patent number. Use legal_search_patents_by_keyword instead when you only have keywords and need to find patents.' It also explains the optional jurisdiction behavior, noting that passing a mismatched jurisdiction is still valid due to normalization, which prevents agent error. This is unambiguous when/not-when guidance.

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