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

Annotations mark this as destructive and open-world; the description adds real context beyond them: existing images survive unless existing='replace', which discards the old image, texts with a video or YouTube link are always left untouched, and the response reports 'applied' vs 'pending' texts. That is meaningful disclosure of side effects and mutation scope that the annotations alone do not convey.

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?

Front-loaded with the core purpose and no filler sentences; every clause carries operational information. It is nonetheless a dense single paragraph, and the long enumeration of selection shapes ('the odd or the even items, the first five, one named text...') is illustrative rather than strictly necessary, which keeps it short of 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?

No output schema exists, yet the description explains the return shape ('applied' with element, item and image content, plus 'pending'), the 40-entry batching rule with continuation in the same turn, the media_targets.image source of valid element kinds, and the video/YouTube exception. An agent has everything needed to call this correctly.

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 coverage is 100%, so the schema already documents all five parameters and the baseline is 3. The description nevertheless adds disambiguation the schema lacks: 'the questions' maps to element 'question' and never to question+choice, 'the answers' means choice, and 'keep' is the value for every ADD request while 'replace' is reserved for explicit change requests.

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 precise verb and resource (adds images to activity texts by searching the Educaplay image bank and a stock library, choosing the best match and attaching it) and explicitly scopes what it does not touch (text, audio). The phrase 'It is the way to add images' separates it from siblings like search_image_library and set_item_images without the agent needing to open any schema.

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?

Gives an explicit trigger ('ONLY when the user asked for images in their own words') and an explicit prohibition ('never illustrate an activity on your own initiative, not even one you have just written'). It also routes selection behaviour (send exactly the user's selection, up to 40 entries, call again in the same turn for the rest) and the keep/replace condition, leaving little to inference.

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