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

Adds substantial context beyond the annotations: a client record may be created as a side effect, an existing open deal short-circuits the create (existing=true), and a permission level is required. Annotations only declare non-readonly, non-idempotent, non-destructive, so these are genuine additions. Failure modes (invalid stage, duplicate phone) are not covered.

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 tight sentences, front-loaded with the operation and immediately followed by the dedupe edge case and the prerequisites. The opening fragment 'A deal by hand' is slightly cryptic but every remaining sentence carries unique information.

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 an 8-parameter mutation with no output schema, the description covers the important surprises (client creation, dedupe return, stage and role constraints) but says nothing about defaults for currency/project, whether amount is optional, or what a successful response contains beyond existing=true.

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 63%, and the description adds meaning for phone (used to find or create the client) and stage_id (must be open), which is real value. However name, amount, and currency are undocumented in both schema and description, and project_id defaults are left to the schema alone.

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 states the concrete operation (create a deal manually, resolving the client by phone or creating one) and the key dedupe rule that returns an existing open deal instead of a second. It is clearly a create tool, but it never names the sibling it should be preferred over (e.g. dosai_update_deal / dosai_move_deal), so sibling differentiation is implicit rather than explicit.

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 real preconditions: the stage must be open (not won/lost) and the caller must be Editor or above. The alternative path — an existing open deal is returned with existing=true — is spelled out. What is missing is routing guidance versus the other deal tools (update/move) when a deal already exists.

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