analyze_images

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

With no annotations, the description carries the full behavioral burden, and it does disclose the important stateful trait: the first call creates a session and later calls with session_id append to that conversation, implicitly reusing the earlier images. However, it says nothing about failure modes (bad path, unreachable URL, expired session), whether sessions persist or time out, or what the call returns — significant gaps for a session-mutating tool with zero annotation coverage.

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?

Three tight sentences, front-loaded with the purpose before the mode behavior and the session mechanic; nothing is padding. There is mild duplication of what the input schema already states about single vs. multiple images and session_id, which keeps it from a 5.

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?

The description adequately covers the multi-turn workflow that an agent most needs to get right, which is the main complexity here. But with no annotations and no output schema, it should also say roughly what is returned (analysis text? per-image results?) and how long a session lives or what invalid image sources do; those absences leave real operational questions unanswered.

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 explains prompt, session_id, and image_sources in comparable detail, including auto-detection of URL/local path/base64. The description restates the one-vs-many semantics and the session creation rule but adds no format, constraint, or edge-case meaning beyond the schema, so the 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?

The description states a concrete verb+resource ("识别图片内容" / recognize image content) and further disambiguates the two operating modes: one image = single-image recognition, multiple images = batch or comparison. It does not explicitly contrast itself with siblings like analyze_video or analyze_document, but the resource distinction is self-evident from those names, so it falls just short of a 5.

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 actionable when-to guidance: pass one image for single recognition, multiple for batch/comparison, and use a session_id on follow-up turns to ask additional questions against the same conversation. It does not state exclusions (e.g., when to prefer analyze_video or analyze_document, or what happens if you mix modes), so a 4 rather than a 5.

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