set_estimate_settings

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

With no annotations, the description carries the full burden and does so well: it discloses partial-update semantics ('Only what you pass changes'), a clearing rule ('an empty client string clears that field'), the 0% default state, reversibility ('undo_last reverses the call'), and a dependency ('Rides export_takeoff'). That is exactly the beyond-schema behavioral context an agent needs for a mutation tool with zero annotation coverage.

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?

Content is dense but front-loaded: field meanings come first, then update/clearing semantics, then the anti-fabrication rule. Nearly every clause earns its place. Minor waste and ambiguity in shorthand like 'Rides export_takeoff' and the compressed margin arithmetic, which force a re-read.

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 6-parameter tool with nested objects, an output schema (so returns needn't be explained) and no annotations, the description covers the important gaps: mutation semantics, defaults, reversibility, and the meaning of nearly every parameter. What's missing is the client sub-field detail and any statement of how this differs from set_pricing, the most confusable sibling.

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 must compensate — and it largely does, defining tax_pct's base, overhead_pct's compounding base (material + labor + tax), and the markup vs margin formulas with a worked example (33.33% margin = ×1.5). It also unpacks the proposal object (itemized vs lump sum, scope_note, inclusions/exclusions one per line, terms, valid_days). The client object is only glossed as 'who the proposal is for', leaving its name/address/reference sub-fields undocumented.

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 names the concrete resources it configures — markups (tax/overhead/profit), proposal text, and client info — and ties them to the underlying canvas fields (estimate_settings, bid_proposal, client_info), so an agent knows exactly what it touches. It never states a crisp verb ('sets/updates') and doesn't contrast itself with set_pricing or revise_proposal, but the resource scope is unambiguous.

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 strong conditional guidance for inputs ('Until markups are set the estimate prices at 0% — say so rather than assume a number'; 'Every price comes from the estimator or a document they gave you'), which tells the agent how to behave while calling. However it offers no guidance on when to choose this tool versus the closely related set_pricing, revise_proposal, or export_estimate siblings, so tool-selection remains implied.

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