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

Goes well beyond annotations (destructiveHint=true, idempotentHint=true) by disclosing the 30-day trash window, the required confirm/expectedUpdatedAt gate, the stale_revision error on concurrent modification, and that retries with the same expectedUpdatedAt are refused with no further effect. It also adds a prompt-injection warning about untrusted CRM field values, which no annotation conveys.

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?

Dense but every sentence carries operational weight, and the destructive semantics are front-loaded before the confirmation protocol. The untrusted-input warning is slightly tangential to invoking the tool, but it is short and safety-relevant.

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?

With no output schema, the description usefully flags the stale_revision return signal, and it fully covers the destructive/confirmation behavior an agent needs. The gap is the undocumented id/objectType/idempotencyKey parameters, which leaves some invocation ambiguity.

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 description coverage is only 17%, so the description carries most of the burden, and it explains two of six parameters in real depth: confirm: true and expectedUpdatedAt as the record's current updatedAt. However, id, objectType, and idempotencyKey remain unexplained anywhere, so the compensation is partial.

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 one record to the trash') and immediately characterizes the operation as reversible-for-30-days rather than an immediate hard delete. It names the sibling restore_record as the recovery path, so an agent can distinguish it from delete_activity, delete_pipeline, or permanent deletion without opening a schema.

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?

Provides explicit preconditions and exclusions: get the user's explicit go-ahead in the same turn, name the exact record, never delete an inferred record, never delete more than one. It also names the alternative route (restore_record) for undoing. This is about as strong as usage guidance gets.

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