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

Beyond the annotations (destructiveHint false, idempotentHint true), the description discloses the blast radius ('changes presentation only, never SQL/API names, data, access or schedules'), the concurrency-detection purpose of expected_main_table_id, the conflict signal layout_changed, and what is returned. It also flags that dry_run validates without persisting, which annotations do not convey.

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?

Purpose and prerequisites are front-loaded and every clause carries actionable information, with no filler. However, the middle section is a dense run of semicolon-chained instructions that mixes prerequisites, conflict handling, and modeling advice, making it harder to scan than a structured list would be.

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 nested-config mutation with no output schema and no parameter descriptions, the definition covers prerequisites, revision concurrency, first-creation handling, conflict recovery, and return value ('Returns the saved layout and revision'). An agent has everything needed to call it correctly and recover from layout_changed without guessing.

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 0%, so the description carries the full load and does: expected_revision's sentinel value 0 is explained, expected_main_table_id's source (chosen_main_table_id) and null-when-absent rule are given, dry_run is defined, and the config semantics are constrained ('exact table IDs, each in at most one section', 'unassigned tables stay visible'). This adds meaning the schema cannot express, since those constraints are not encoded in the JSON 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?

The description opens with a precise verb and enumerates the exact resource saved: ordered sections, table display titles/descriptions, collapsed state, and the default opening table. It also scopes the effect ('presentation only, never SQL/API names, data, access or schedules'), which separates it from update_dataset. It never names or contrasts with the sibling configure_table_view, so an agent must infer the boundary between dataset-level layout and per-table view configuration.

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 explicitly routes the agent through the prerequisite read ('Read get_my_dataset for dataset_layout and its revision'), states the edge case ('use expected_revision 0 only when absent'), and gives conditional guidance for first creation via expected_main_table_id. It also prescribes response behavior on conflict ('on layout_changed reread and reconcile instead of overwriting') and a safe trial path via dry_run.

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