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

Annotations declare the safe/mutating profile, and the description adds non-obvious behavior: optimistic concurrency via revision with 409 conflict semantics, the evidence policy (public signals can't establish payment intent, milestones need attributable evidence), and explicit negative scope ('does not contact businesses or execute delivery'). It does not mention that the operation is non-idempotent, which matters for retry safety.

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 a distinct point (mutation model, conflict handling, evidence policy, scope limits), with the core action front-loaded. 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?

For a 10-command dispatcher over deeply nested objects, the description covers policy and failure modes well and an output schema exists to describe returns, but it gives no per-command guidance or idempotency/retry caveat. An agent can call it, yet could easily send a wrong command shape.

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 33% but nested objects carry their own inline descriptions (patch, validation), and the description ties 'revision' to the conflict model. Still, it never explains which fields each command type consumes or that command.type selects the whole shape, leaving the biggest semantic question to the schema.

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: apply one validated command against an opportunity workspace at a given revision. The 10 concrete command types that define the actual capability set are only in the schema enum, not the description, so an agent can't grasp the full scope from prose alone.

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?

Adds a clear retry rule ('409 means re-read before retrying') which is real usage guidance, but never says when to use this versus siblings like get_opportunity_workspace, create_opportunity_workspace, or research_opportunity_workspace. The reader must infer the read/write split from tool names.

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