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

Annotations already establish readOnly=false, destructive=false, and openWorld=true, so the description is not carrying the safety burden. It adds genuinely useful context the annotations cannot express: that credits are consumed, that the run is saved, and that repeated calls with the same idempotency_key return the original result instead of re-spending. The retry-safety claim sits in mild tension with idempotentHint=false, which reads as the keyless behavior, so this is short of 5.

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?

Four short sentences, front-loaded with verb and resource, then consequences, prerequisites, and return value in descending priority. No sentence is redundant with the name or 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 credit-spending, state-mutating call with no output schema, the description covers the essentials: what is produced, that it costs credits, that it persists, and how retries behave. It stops short of full completeness because several parameters (body/query overrides, brand_id, workspace_id) are never addressed and it does not describe the shape of the returned result beyond calling it 'the generated result'.

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?

With 7 params at 57% schema coverage, the description usefully supplements the two most important inputs: it ties 'id' to the templates returned by aidelly_list_prompts and explains input_values as the template variables. The retry semantics attached to idempotency_key add meaning the schema only implies via an example and pattern. body, query, brand_id, and workspace_id remain unexplained, keeping it at 4.

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 first sentence gives a specific verb and resource ('Run a saved prompt template by id'), and the following sentences state the full consequence set: an AI result is generated, credits are spent, and the run is persisted. The tool is clearly distinguishable from siblings like aidelly_list_prompts (the id source) rather than the runner.

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 routes the agent to the correct prerequisite by stating 'Template ids come from aidelly_list_prompts,' which is actionable usage context. It lacks any explicit when-not condition or comparison against adjacent generation tools (e.g., aidelly_generate_analytics_insights), so it stops short of full 5-level guidance.

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