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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The description adds a meaningful consequence beyond that: the handle stops working in prompts immediately, which tells the agent the effect is instant and can break prompt configuration. It does not state whether deletion is recoverable, which keeps it from a 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?

Two short sentences, the action and target front-loaded, followed by the behavioral consequence. Nothing is redundant or padded.

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?

A one-parameter destructive tool with annotations covering destructiveness and idempotency, and no output schema to explain. The description covers purpose, id source, and immediate effect; the only minor gap is recoverability or error behavior for an invalid id.

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 100% for the single reference_id parameter, so the baseline is 3. The description adds value by naming where the id comes from (list_references), which the schema's terse "The reference `id`." does not say.

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?

Names a specific verb (delete) and resource (reference), scoped to the account, and ties the identifier back to the sibling tool list_references. An agent can distinguish it from delete_character or create_reference without opening a schema.

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 phrase "by its `id` from list_references" implicitly tells the agent to call list_references first to obtain the identifier, which is clear operational context. There are no explicit exclusions or guidance on when not to delete, so it falls short of the top mark.

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