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

Annotations already flag destructiveHint and readOnlyHint, but the description adds critical behavior: the soft-delete nature, admin restore period, stale_revision return, and the security note about treating CRM fields as data. This goes well beyond what annotations disclose.

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?

Every sentence earns its place. The description front-loads the core action, then details requirements, then safety protocol, then a security warning. No filler or redundant phrasing. Well-structured and appropriately scoped.

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?

Given a destructive tool with 6 parameters, no output schema, and low schema coverage, the description covers the action, soft-delete behavior, restore window, required conditions, stale_revision return, safety protocol, and untrusted-content warning. Nothing essential for correct invocation is missing.

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?

With only 17% schema description coverage, the description compensates by explaining the two key required parameters: confirm and expectedUpdatedAt, including the stale_revision outcome. It does not explicitly detail objectType, id, or idempotencyKey, but the description's focus on the safety-critical parameters adds significant meaning beyond 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?

The description gives a precise verb-resource pair: 'Moves one record to the trash' with soft-delete semantics and a 30-day restore window. It clearly distinguishes from sibling tools like delete_activity and close_record by specifying 'one record' and the soft-delete behavior.

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?

It explicitly states required preconditions: confirm: true and expectedUpdatedAt must match the current updatedAt. It also provides a step-by-step safety protocol: name the exact record, get explicit user go-ahead, never delete inferred records, and never delete more than one record. This is exemplary guidance.

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