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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description meaningfully adds that creation 'may trigger the workflows and notifications set up in the CRM' and that the customer code must be unique (omitted → auto-generated). It does not mention auth requirements or error behavior on duplicate codes.

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?

The mutation intent is front-loaded in the first word, and the four sentences each convey distinct constraints (uniqueness, name-matching, optional contact, side effects). The enumeration of name-matched fields is slightly dense but every clause earns its place.

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 20-parameter nested-object mutation with no output schema, the description covers the tricky constraints well but says nothing about what is returned (e.g., created account id) and omits custom_fields entirely. Adequate but with a clear gap for an agent needing to chain on the result.

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?

With only 65% schema coverage across 20 parameters, the description carries real weight: it explains that account_code is unique and optional, that type/source/industry/relationship/country/province/district/ward must be matched by configured NAME (a non-obvious constraint), and that contact is a single optional primary contact. It leaves custom_fields and the return/ID behavior unaddressed.

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 opens with a specific verb and resource ('Create a new customer (account)') and the 'WRITE:' prefix immediately signals mutation, distinguishing it from read siblings like getfly_get_account and getfly_list_accounts as well as from getfly_update_account.

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?

It clearly establishes the create context and adds operational rules (unique account_code, names must match Getfly-configured values, one optional primary contact). It also cross-references getfly_list_users for account_manager_username. However, it never explicitly contrasts with getfly_update_account for the case where the customer already exists.

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