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

Annotations give readOnlyHint=false and openWorldHint=true, yet the description says nothing about what is actually fetched, billing/rate limits, or what happens when claims are unavailable (the schema's replaceByRelated hints at that failure mode but the description never explains it). The 'Retrieves' framing also sits awkwardly against readOnlyHint=false, leaving the agent unsure of the safety profile.

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 dominated by a repetitive trigger-keyword list that restates 'patent claims, independent claims, dependent claims' twice and repeats 'Nexscope' several times. The actual useful content (retrieval purpose plus the by-ID/by-number invocation rule) could be delivered in two sentences.

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?

With no output schema, the description should characterize the returned claims structure (tree, counts, scope) more concretely, though the keyword list loosely gestures at it. All three parameters are schema-documented, so the main remaining gap is return-shape and unavailability behavior rather than input guidance.

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%, so the schema already documents patentId, patentNumber, and replaceByRelated including the 100-value comma-separated limit. The description only restates that lookup can be 'by patent ID or publication number' and adds no new semantics such as how the two identifiers interact or when to prefer one. Baseline 3 applies.

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?

States a specific verb and resource ('Retrieves patent claims data from Nexscope') and names the concrete artifacts it returns (claims text, independent/dependent claims, claim count, claims tree). It does not explicitly distinguish itself from close siblings like nexscope_patent_claims_translation or nexscope_patent_description_data, so an agent must infer the boundary.

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?

It gives invocation context ('trigger when the user mentions patent claims' and 'by patent ID or publication number, even without explicitly mentioning Nexscope'), which is useful routing information. But there is no when-not guidance, no alternative named (e.g., the translation variant for non-English claims), and the trigger list is a keyword dump rather than a decision rule.

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