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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine behavior beyond that: deterministic parsing, native DATEV EXTF detection, the period-header heuristic, re-detection rules on override, and the explicit note that the raw binary is not returned.

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?

It is a single dense paragraph but front-loads the core purpose and return shape before the detection and override details. Nearly every clause carries information, though the period-format enumeration and parenthetical examples make it heavier than strictly necessary.

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 complex tool with a nested `structure_override` object and no output schema, the description names the key returned artifacts (sheet summaries, `detected_periods`, `period_range`, `suggested_structure`) and covers the main detection/override behaviors. Minor gaps remain on full response shape and error conditions, but the agent has enough to call it correctly.

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 baseline would be 3. The description rises above it by explaining the intent behind parameters—why `structure_override` exists (Débit taken as value, account-code taken as label, wide sheets with too few period columns) and what omitting `sheet_name` produces.

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 and resource ('Parses an uploaded Excel/CSV (`file_id`) deterministically') and immediately names what it returns, which sharply separates it from the write-side sibling `layerz_import_branch`. An agent can tell this is the inspect/parse step versus an import.

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 gives conditional guidance for parameters (omit `sheet_name` for summaries only; use `structure_override` when a ledger is misdetected or a wide sheet has <3 period columns). However, it never states when to reach for this tool versus alternatives such as `layerz_import_branch`, leaving tool-level selection to inference.

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