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

The description presents this as a pure retrieval ("Retrieves ... images"), yet annotations declare readOnlyHint=false, an inconsistency that leaves the agent unsure whether the call has side effects. Beyond that it adds no behavior the annotations or schema do not already cover: no statement of return format (image URLs vs. binary), no batch behavior, no failure modes for unresolved IDs.

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 first sentence is well-formed and front-loaded, but the remainder is a keyword-stuffed trigger list with heavy redundancy ("patent abstract drawings / patent drawings / patent images / patent abstract images / abstract image lookup"), which pads the length without adding discrimination 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?

For a two-optional-parameter retrieval tool with no output schema, the definition covers source, lookup keys and activation context adequately; it only omits what the returned image payload looks like, which matters when there is no output schema to fall back on.

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% and the schema already documents the precedence rule (patentId over patentNumber), the 100-ID comma-separated limit, and the max length. The description merely restates "by patent ID or publication number," adding no syntax, format examples, or guidance on which identifier to prefer.

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 first sentence gives a specific verb, resource, source database and lookup keys ("Retrieves patent abstract images (drawings) from the Nexscope patent database by patent ID or publication number"), which is unambiguous. However, it never distinguishes itself from close siblings such as nexscope_patent_fulltext_images or nexscope_data_zy_abstract_image, so an agent choosing between patent-image tools still has to guess.

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 trigger-keyword list plus "Also trigger when the user needs to view the drawings or figures in patent documents" does give a usable activation cue and even extends beyond explicit Nexscope mentions. But there is no when-not guidance: nothing says to use nexscope_patent_fulltext_images for full-text figures, or the Zhihuiya variants for other databases, which are the realistic alternatives here.

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