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

Beyond annotations (which only mark mutation/non-idempotence), the description adds valuable behavioral context: the result is a draft-status template, the required scope is templates:manage, and the operation maps to a single known HTTP endpoint with shared billing/rate limits. It also warns not to invent alternate paths. It does not describe what the response contains or how a draft becomes published, but annotations already flag the mutation profile.

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?

The description is short and front-loaded, with useful scoping and endpoint guardrails in the final lines. The only waste is the redundant first line 'Create a template' immediately followed by the same statement; otherwise every sentence earns its place.

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?

This is a high-complexity create operation with 15 parameters, deep nested structure, and no output schema, yet the description provides no lifecycle context beyond 'draft status' and no indication of the response shape or how to reference the created template afterward. The scope and endpoint info is useful but not sufficient for an agent to fully understand the consequences of the call.

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?

The description adds no parameter-level meaning, and schema coverage is only 47% (below the 50% threshold), so the description was expected to compensate for undocumented structure fields. Required fields like name, pass_style, and structure are discoverable from the schema, but many nested properties and image/override parameters remain unexplained by both the schema and the description.

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 opens with a clear verb and object and specifies a unique state: 'Creates a new pass template in draft status.' This distinguishes it from updateTemplate, publishTemplate, and listTemplates, and the explicit OpenAPI operationId and POST /manage-templates mapping leave no ambiguity about the intended action.

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?

Usage is implied through 'create' and 'new', but the description never states when to choose this over siblings or when not to use it. It does provide useful preconditions (templates:manage scope, same API billing/rate limits), so there is some guidance beyond pure tautology.

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