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

Annotations already declare readOnly=false, destructiveHint=false, idempotent=false, so the safety profile is covered; the description goes beyond them with the sharing model ('Shared prompts are visible to your whole workspace'), the per-creator permission boundary, placeholder substitution semantics, and a prompt-injection caution that prompt text is customer data, not instructions. It does not say what the call returns or what happens to omitted fields on update, which is the main remaining gap for a mutation.

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 front-loaded sentences carry the create/update split, the sharing and permission model, and the placeholder rule with almost no waste. The trailing 'Free.' is terse but useful cost information, and the injection warning earns its place given the tool stores text later fed to a model.

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 an 8-parameter mutation tool with no output schema and 25% schema coverage, the description covers the modes, permissions, sharing, and template semantics well. It leaves unaddressed the update merge behavior (whether omitted fields are preserved), the meaning of system_instruction and is_shared, and any indication of the returned object, which an agent would want before calling.

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 only 25% across 8 parameters, so the burden falls largely on the description; it compensates for name, prompt_template, and prompt_id by tying them to actions. It says nothing about model (only the schema's 'Model id from list_models' hints at it), is_shared, category, or system_instruction, leaving half the parameters undocumented in both places.

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 specific verb (save) and resource (prompt) and splits the operation into the two modes the schema exposes: 'action create: name and prompt_template' and 'action update: prompt_id and the fields to change'. That is enough to distinguish it from get_prompt, list_prompts, and delete_prompt, though it never names those siblings or explicitly routes to them.

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 concrete when-to-use guidance by mapping each action to the fields required: create needs name and prompt_template, update needs prompt_id plus changed fields. It also states the ownership condition for updates ('only the creator can change or delete a prompt'). It stops short of naming alternatives such as preview_prompt for testing a template or list_prompts for finding a prompt_id.

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