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

Goes well beyond the annotations by disclosing reversibility ('the person can restore it'), the permission model (delete permission plus editor access, and where to find those permissions), and the exact return payload including a localized userMessage. For a destructiveHint=true mutation, this is exactly the context an agent needs.

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?

Three sentences ordered as purpose, constraints/permissions, then returns — front-loaded with zero filler. Every clause carries a distinct, actionable fact.

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?

No output schema exists, so the description explicitly enumerates the return fields, and it also covers reversibility and authorization prerequisites. An agent has everything needed to decide and call correctly.

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?

Only one parameter, and schema coverage is 100% with the description already stating its provenance ('from list_diagrams or create_diagram'). The description adds no format or constraint detail beyond the schema, so 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 and resource ('Moves a diagram to the trash') and immediately bounds the semantics: soft delete, restorable, not permanent deletion. This distinguishes it clearly from sibling tools like revert_change or apply_ops without needing their schemas.

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?

Gives an explicit usage condition ('at the person's request', 'only for a diagram the person asked to delete') and rules out permanent deletion, which is strong when-to-use guidance. It does not name a specific alternative tool (e.g., revert_change for restoring), so it stops short of the top tier.

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