eduframe-mcp

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

Annotations already declare this as destructive, idempotent, and non-read-only, but the description adds no behavioral context beyond these structured hints. It fails to clarify whether deletion is permanent, what happens to associated objects currently using this label, or whether the operation can be reversed. The agent gains no additional safety or operational context from the description text.

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 single sentence 'Delete a label' is brief but constitutes under-specification rather than efficient, valuable communication. It front-loads no critical context about implications, constraints, or return values. The extreme brevity leaves significant gaps in the agent's understanding despite consuming minimal tokens.

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 destructive operation affecting a resource with clear relationships to other entities (evidenced by sibling `add_label_to_order`), the description inadequately addresses cascading effects or dependency checks. No output schema exists to clarify return values, yet the description fails to compensate by explaining success/failure states or idempotency behavior. The minimal description creates operational risk for a destructive tool.

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 input schema has 100% description coverage, with the `id` parameter explicitly documented as 'ID of the label to delete'. The description adds no additional semantics, validation rules, or format examples beyond what the schema provides. With the schema carrying the full descriptive burden, the baseline score applies.

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 'Delete a label' merely restates the tool name 'delete_label' without expanding on scope, side effects, or specific resource constraints. It fails to distinguish this tool from sibling operations like `update_label` or clarify the permanence of the deletion. While not misleading, it provides no semantic value beyond the function name itself.

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 description offers no guidance on when to use this tool versus alternatives such as `update_label` (for modifying existing labels) or prerequisites such as removing label associations. It omits critical preconditions like whether the label must be unassigned from orders (via `add_label_to_order`) before deletion. No exclusions or error conditions are specified.

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