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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds real value beyond that by scoping the blast radius: only the reference alias is removed, while the underlying image persists. It does not say whether deletion is reversible or how an unknown id is handled.

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, zero waste, with the core effect front-loaded and the scoping caveat directly after it. Every clause 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?

For a one-parameter destructive tool whose annotations already carry the safety hints and with no output schema to explain, this is essentially complete: what it deletes, what survives, and where ids come from. Only reversibility and error behavior on a bad id are absent.

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?

Single parameter with 100% schema description coverage, so the schema already documents referenceId including its provenance. The description's '(ids from list_references)' merely restates that, adding no format or failure-mode detail. Baseline 3 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?

States a specific verb (delete) plus resource (named reference) and immediately defines the semantic consequence: the @Name stops working in prompts. That distinguishes it cleanly from list_references, create_reference, update_reference, and from library-file deletion tools.

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?

Names list_references as the source of valid ids, which tells the agent what to call first. The clause 'the image itself stays in the library' implicitly steers agents away from library-file deletion when they only want to remove the alias. No explicit when-not guidance or named alternative for the opposite operation (create_reference), so not a 5.

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