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

Goes well beyond the annotations: it discloses the upsert-by-code matching mechanism, the side effect that assigning a role removes it from the account that had it, the conditional restrictions on type and archived, and the per-call cost with the 'nothing if it fails' caveat. These are exactly the mutation and billing traits an agent cannot infer from readOnlyHint/idempotentHint alone.

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-loaded and generally efficient, but roughly half the text is a verbatim enumeration of the 19 role values that already exist as a schema enum, so a large share of the description repeats structured data. The valuable parts (matching, restrictions, side effect, cost) are stated once and early.

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 batch upsert tool with no output schema and no structured parameter docs, the description covers matching, mutation constraints, side effects and cost. The one gap is what the call returns (per-account success/error, new codes applied), which an agent would want since there is no output schema to consult.

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 0% schema description coverage, the description carries the weight and does so: it enumerates every accepted field and adds semantics the schema lacks, such as 'type only while unused', 'archived only with no balance and no role', IBAN clearing via empty string, and the meaning of roles as the accounts the books post to automatically. Only the batching limits and new_code interaction are left 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 clear verb pair (add or change) on a specific resource (accounts) and names the matching key (code), so an agent immediately knows this is an upsert against the chart of accounts rather than the read-side books_list_accounts. It stops short of naming any sibling explicitly, so it is clear but not fully differentiated.

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 concrete conditions that select behavior: 'type (only while unused)' and 'archived (only with no balance and no role)', plus the rule that assigning a role steals it from the previous holder. That is real guidance on when certain changes are permitted, though there is no explicit statement of when to call this versus books_setup or other account-related tools.

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