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

Annotations already declare destructive=true and idempotent=true, yet the description adds real value beyond them: the won/lost stage rejection, the optimistic-concurrency failure mode ('fails if a deal moved since it was read'), and the precise retry semantics of idempotencyKey. The notable omission is atomicity – whether a partial batch failure rolls back the whole batch or applies some movements, which matters greatly for a destructive bulk operation.

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?

Four short sentences, each carrying distinct information (batch cap, stage restriction, concurrency failure, idempotency). The most decision-relevant constraint, the 100-deal scope, is front-loaded and there is no filler.

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?

Covers preconditions and retry semantics well for a destructive nested-object tool, but with no output schema the agent still cannot learn whether the call is atomic, what a partial failure looks like, or what close_date does. For a bulk mutation with three required fields per movement, those gaps are material.

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 50% and the description explains idempotencyKey reuse behavior, reinforcing what the schema already states. However, it never maps expected_revision or expected_stage_id to the 'deal moved since it was read' failure, and close_date goes unmentioned entirely, so the nested movements parameters remain only partially explained.

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 with hard scope bounds: moves up to 100 deals to a single stage. It also draws an explicit line against the sibling moveDeal ('closes deals one at a time'), so an agent can distinguish bulk from single-deal moves without inspecting either 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?

Gives concrete usage conditions: won/lost stages are rejected, and moveDeal is named as the one-at-a-time alternative. It stops short of an explicit rule such as 'use moveDeal for a single deal, use this for two or more,' so the selection logic must be inferred, but the context is clear.

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