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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true. The description adds valuable context beyond those: it clarifies this is a configuration action rather than a posting action, states that unmapped categories cannot post, and explains the approval behavior ('first use may require a manager's approval... the card is the yes — do not re-ask in chat'). It does not contradict the annotations. The only minor gap is that it doesn't detail what happens to an existing mapping when overwritten, but the description still adds substantial behavioral context.

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 description is compact and front-loaded with the core mapping purpose, then the usage condition, then the routing and approval notes. The approval note is somewhat long and chatty ('the card is the yes — do not re-ask in chat'), but it conveys important operational guidance. Every sentence earns its place; a small deduction for the slightly verbose approval section.

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 config-mutation tool with no output schema, the description covers the purpose, the usage context, the downstream effect, and the approval workflow. It doesn't describe the return value or what happens on overwrite, but the description is otherwise complete enough for an agent to call it correctly. The sibling list includes list_xero_accounts and post_xero_transaction, which the description references, helping the agent navigate the tool ecosystem.

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 all four parameters. The description adds context for fo_category ('the account name on a transaction') and xero_account_code ('from list_xero_accounts'), which reinforces the schema. However, it doesn't add meaning beyond the schema for companyId or xero_account_id, and the description doesn't explain the relationship between xero_account_id and xero_account_code. Baseline 3 is appropriate because the schema carries the parameter documentation burden.

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 states a specific verb ('Map'), a clear resource (FreedomOS cash-flow category to Xero account code), and the downstream purpose (so suggest_xero_post / post_xero_transaction can book it). It also explicitly distinguishes this from posting by saying 'Does not post anything' and 'config, not a post', which separates it from sibling tools like post_xero_transaction and suggest_xero_post.

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?

The description explicitly says 'Use when the operator is setting up books posting' and states the consequence of not using it ('Unmapped categories cannot post'). It also includes routing guidance ('Map FO category → Xero account code (config, not a post)') and approval-tier instructions that tell the agent when to call and how to handle approval. This is strong, actionable usage guidance.

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