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

Beyond the annotations (destructiveHint/idempotentHint true), it discloses exactly what comes back — same id, status, page, ticket tiers, questions, guest list, and every date of the series — plus the retention constraint tied to the member's plan and the no-op failure mode. That is real behavioral context an agent cannot get from the hints.

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?

A single front-loaded paragraph that opens with the trigger condition and then layers restore fidelity and failure behavior. It is dense but every clause carries information; the parenthetical about plan-based Trash windows is the only slightly buried detail.

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-required-parameter mutation with no output schema, the description covers outcome, preconditions, and failure reporting well. Minor gap: dry_run's semantics (a preview that restores nothing) are left entirely to the schema, which is defensible but would be worth a phrase for a destructive operation.

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 the baseline is 3. The description adds provenance meaning for event_id (the value returned by connections_event_delete) but says nothing about dry_run, person, or project, leaving those to the schema.

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 ('Brings the event back from Trash') and enumerates the trigger phrasings ('undo that', 'I deleted the wrong event'), which separates it cleanly from connections_event_delete and connections_storage_restore_from_trash.

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 explicit when-to-use conditions, names the sibling to consult for Trash state (connections_storage_list_trash), specifies which id to pass and where it came from (connections_event_delete), and states the when-not case: if the event is not in Trash or a resource like its web address was taken, nothing changes and it explains why.

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