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

Annotations already declare openWorldHint=true and a destructive/idempotent profile, but the description adds no behavioral context of its own — nothing about caching (no_cache), cost (ai_overview billing), or pagination semantics that the schema hints at. For a 28-parameter scraper it should say more than 'triggered when'.

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?

A single front-loaded sentence with no filler, which is appropriately sized for a trigger statement. It is efficient, though the extreme brevity is partly what leaves the definition thin elsewhere.

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?

Against 28 parameters, a required query, no output schema, and a defaulted tbm=isch mode, the description is far too sparse. It omits return format (json=1..4), pagination (start), device targeting, and cost implications — an agent would have to reverse-engineer all of that from the schema.

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 all 28 parameters are fully documented in the schema itself. The description only loosely echoes the filter dimensions (size, color, type, copyright) that map to tbs/cr/lr, adding no syntax or default guidance beyond what the schema provides — baseline 3.

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 names a specific verb and resource: searching image results via Google Images, plus the filterable attributes (size, color, type, copyright, location, language). It is clear what the tool does, but it never distinguishes itself from siblings like bing_images or google_lens, which could also surface imagery.

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?

Framed entirely as a trigger condition, it states when to reach for this tool (image search or filtered image search). It gives clear positive context but no exclusions and names no alternative, so an agent choosing between google_images, bing_images, and google_lens gets no routing help.

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