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

The description adds real behavior beyond annotations: dedup on identical text, a 2000-character cap, and the returned `characters_prompt_uuid`. However, annotations declare destructiveHint=true and the description never explains what is at risk (overwriting an existing prompt for that kind?), and the 'same text twice is kept once' claim sits in tension with idempotentHint=false without clarifying the distinction.

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 dense sentence with the write marker and the kind taxonomy front-loaded, then limits and return value. No filler, no restatement of the title.

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 2-parameter write tool with no output schema, naming the returned `characters_prompt_uuid` and the character limit covers most of what an agent needs. The remaining hole is the destructiveHint=true annotation, which the description never reconciles with the benign-sounding 'save' action.

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 0% and `kind` has no enum in the schema, so the description is doing the heavy lifting by enumerating the five allowed values. It also gives the `text` bound (2000 characters) and the dedup rule that affects how text is stored. Only minor gaps remain, such as format expectations for `text` or whether one prompt per kind is enforced.

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?

Specific verb (Save) plus specific resource (a character prompt) scoped to the caller's studio list, with the [write] marker disambiguating it from list_character_prompts and delete_character_prompt. The enumerated `kind` values (looks | outfits | poses | locations | profiles) make the object of the save unambiguous.

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 write intent and the kind taxonomy imply when to call it, and the 'same text twice is kept once' note hints at safe re-saving. But it never says when to prefer this over list_character_prompts (to check existing prompts) or delete_character_prompt (to replace one), and there are no stated prerequisites or exclusions.

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