save_estimate

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

Annotations already declare non-destructive, idempotent, open-world write semantics, so the bar is lower. The description adds that a 'confidential human link' is returned and that certain fields become mandatory per kind, but says nothing about failure behavior, permissions, or what happens if a save is retried with a stale catalogVersion.

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?

Three short sentences with the gating condition front-loaded and no filler. The snippet is dense and every sentence carries information, though the kind-specific requirements could be formatted as a compact conditional list for faster scanning.

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 nested write with a rich schema and no output schema, the description covers the precondition, the per-kind required fields, and the return artifact. The omission of catalogVersion semantics and retry/failure guidance is a modest gap given how much the schema already documents.

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 only 40% schema description coverage, the description compensates by summarizing the cross-field conditional (kind drives which plan fields become required), which the oneOf schema encodes structurally but does not spell out. catalogVersion remains unexplained in both places, so it does not fully close the gap.

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 verb (save) and the operation's gating condition, plus per-kind requirements ('Group/biggroup require organizer and retreat title; resident requires guest name'). This is clearly distinguishable from read-oriented siblings like get_estimate or calculate_quote, though it never names edit_estimate as the path for modifying an existing estimate.

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?

'Save after explicit user request' establishes a clear precondition tied to the userConfirmed parameter, which is more useful than generic when-to-use text. It does not name alternatives or exclusions (e.g., use edit_estimate to modify, use calculate_quote to preview), leaving that routing to inference.

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