etabs_what_changed

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

The description is behaviorally rich (statefulness, baseline capture, manual-edit detection), but it directly conflicts with the structured annotations: 'since the last call' plus 'the first call records the baseline' means repeated identical calls produce different results and mutate baseline state, which contradicts idempotentHint=true and sits awkwardly with readOnlyHint=true. This is an annotation contradiction.

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 with the core answer ('What changed... since the last call') and three tight sentences with no filler. The long mid-sentence enumeration of categories is dense but each item is informative.

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?

An output schema exists, so return formatting need not be described. The description covers statefulness, diff scope, and baseline behavior — sufficient for correct invocation. Minor gaps remain around the limit parameter's truncation behavior and whether diffs persist across calls.

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 coverage is 50% — reset is documented in the schema ('Only record a new baseline'), limit is not. The description supplies the concept of a baseline that gives 'reset' meaning, but it never mentions 'limit' or what truncation does. Marginal added value over 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 specific operation (report what changed in the model) and enumerates the tracked categories — objects, sections, loads, combos, groups, stories, units, lock, file. This clearly separates it from siblings like etabs_model_overview (current state) or etabs_list_objects (enumeration).

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?

Explains the triggering context well: it reports edits made by hand in the ETABS window so the agent can re-sync, and notes the first call establishes the baseline. It does not name an alternative tool (e.g., etabs_model_overview or etabs_list_objects) for when a full-state read is preferred over a diff.

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