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

Annotations already flag destructiveHint=true and idempotentHint=false, so the safety floor is covered; the description earns credit by adding what annotations cannot: the item goes to the member's Trash (i.e. recoverable), and a dry_run preview is the sanctioned precondition. It also explains the human-confirmation requirement before committing.

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?

Front-loaded with the trigger condition, then the id source, then the safety protocol, then the alternative. Every sentence carries a distinct decision or safety fact; nothing is padding.

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 mutation with no output schema, the definition covers trigger, id provenance, recoverability (Trash), the dry_run gate, confirmation, and the sibling alternative. That is everything an agent needs to call this safely and 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?

Schema coverage is 100%, so id, person, dry_run, and project are all documented, and the dry_run description already states the preview-then-confirm protocol. The description repeats that guidance rather than adding syntax or format detail, so this sits at the baseline.

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 first clause states a specific verb (delete/remove) and resource (a to-do), and immediately narrows the case ('usually an accidental duplicate'). Sibling differentiation is explicit: connections_todo_done is named as the alternative for completed items, and connections_todo_list is cited as the id source.

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 when-to-use (member asks to delete/remove), when-not (completed item → connections_todo_done), and an operational protocol (call dry_run: true first, confirm with the member, then the real call). No inference is required to pick between delete and done.

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