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

Adds rich context beyond annotations: acceptance window start/restart semantics, base64 landing on object storage, envelope encryption for secrets, and the Bitroad acceptance check flow with pass/fail consequences. Annotations only cover mutation safety; the description carries real behavioral weight.

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?

Front-loads the purpose and key kind semantics, but the final sentence on acceptance verdicts is dense and somewhat tangential to invocation. Every sentence earns some place, yet the paragraph is weighty for a call-time reference.

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?

No output schema, so the description valuably explains the acceptance_verdict return behavior and payout consequence. For a mutation tool with rich annotations, it covers most of what an agent needs; only retry/error semantics are unaddressed.

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%, so the schema fully documents the kind enum, file fields, and constraints. The description adds the 25 MB limit and the kind list, but largely restates what the schema already provides; baseline 3 applies.

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 (submit), resource (the deliverable), and the seller-side role and quote state (paid/in-progress quote). It is clearly distinct from siblings like services_start_work and services_accept_quote.

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?

Implies when to use it (after work, on a paid/in-progress quote) and routes to services_get_quote for acceptance_detail. It doesn't explicitly exclude alternatives or state prerequisites like 'must be the seller', but the context is solid.

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