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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, but the description adds genuinely useful behavioral context beyond them: the record includes credit terms, the operation is not deduplicated, no message is sent, and the RFC must pass tax-authority validation. These details materially affect how an agent should sequence calls and what side effects to expect.

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?

Five short sentences, each earning its place: purpose, write behavior and non-deduplication, the dedup check, the RFC rule, the side-effect note, catalog sourcing, and endpoint. The critical caveat (not deduplicated) is front-loaded near the start.

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 13-parameter mutation tool with no output schema and a nested address object, the description covers the key behavioral risks: non-idempotency, no messaging side effect, catalog dependencies, and RFC constraints. It could be slightly more complete by mentioning what the call returns (e.g., the created client id) or permission requirements, but the essential invocation guidance is present.

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 description coverage is 100%, so the schema already documents every parameter. The description still adds value by naming the sibling catalogs that supply price_list_id and location_id and by explaining the RFC validation rule and the generic RFC fallback, though it does not cover all 13 parameters at the same depth.

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 ('Create a customer in Bind ERP') and immediately distinguishes it from related operations by naming the deduplication check against binderp_list_clients and the catalog lookups needed. An agent can tell this apart from binderp_create_prospect or binderp_create_order without opening any schema.

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 explicit preconditions and alternatives: check binderp_list_clients for the RFC first because the operation is not deduplicated, pull price_list_id and location_id from binderp_list_catalog, and ensure the RFC is valid or use the generic XAXX010101000. This is clear when-to-use guidance with concrete routing to sibling tools.

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