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

Goes beyond annotations by disclosing a real side effect (a move to won/lost withdraws the deal's open cards) and a failure mode (a lost move without a valid lost_reason is refused, naming the valid reasons). Annotations already cover safety/idempotency, so this added behavioral context is the description's real contribution.

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?

Three tight sentences, front-loaded with the core action, then the prerequisite (list_stages), then conditional requirements and side effects. No wasted wording.

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 covers the mutation, its prerequisites, its refusal behavior, and its side effect, which is sufficient for correct invocation. A note on auth/permissions or the response shape would make it complete, but nothing critical 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?

Schema coverage is 67%, and the description meaningfully extends the schema: lost_reason must be one of the organization's lost reasons, and stage_id is resolved via list_stages. This adds constraint semantics beyond the bare field definitions.

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+resource (move a deal to a stage) and adds the key relationship that the pipeline follows the stage, which helps disambiguate it from update_deal. It's clear on its own, though it doesn't explicitly contrast itself with the sibling update_deal or create_deal.

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?

Routes the agent to list_stages to resolve stage_id and implies read_the_lost_reasons for valid lost reasons. It states the condition (move to lost stage) under which lost_reason is mandatory, but doesn't spell out when to prefer this over update_deal.

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