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

Annotations say it mutates but isn't destructive, so the description's job is to add operational context — and it does: the move is audit-logged ('the deal's history records who moved it') and requires Editor role or above. Those are exactly the facts an agent needs before invoking a write. It still doesn't say whether the move is reversible or what happens to open tasks/notes on the deal.

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?

Two sentences plus a short permission fragment; the core action and the lost-reason rule are front-loaded, and nothing is repeated or padded.

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 4-param mutation with no output schema, the definition covers the action, the terminal-stage special case, the audit consequence and the permission requirement. What's missing is error/edge behavior (invalid stage, same-stage move) but that is a minor gap here.

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% and each parameter already names its source list endpoint, so the schema carries parameter meaning. The description only reinforces the 'reason' parameter's conditional use for lost stages, which the schema already states — marginal added value.

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 ('Move a deal') plus the destination object ('a stage of its CRM project'), and clarifies that terminal stages (won/lost) are included. An agent can distinguish it from dosai_update_deal (field edits) by the stage-transition framing, though it never names that sibling explicitly.

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 an in-context rule ('for lost give the reason in words') and a permission gate ('Editor or above'), which are real usage conditions. However, it never says when to prefer this over dosai_update_deal or what to do if the target stage doesn't exist, so the routing guidance is implied rather than stated.

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