draft_estimate

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

No annotations are present, so the description carries the full burden of behavioral disclosure. It does disclose a key behavioral trait: the operation only saves a draft and never sends, approves, or accepts it, and 'auditable' implies persistence with an audit trail. However, it does not mention permissions, idempotency, or behavior when project_id is invalid, leaving meaningful gaps.

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?

The description is two concise sentences with no filler. The main action and constraint are front-loaded, and the second sentence efficiently delivers the only non-obvious parameter detail: line item requirements.

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 values do not need explanation. However, with no annotations and a 9-parameter input, the description only partially covers usage context and parameter semantics; top-level required fields and explicit sibling alternatives are left to the schema and tool name. It is reasonably complete for a straightforward draft-save operation but not thoroughly contextual.

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 0% schema description coverage, the description must compensate; it does so for the line_items object by listing required fields (description, quantity, unit, unit_cost) and noting evidence_ids is optional at that level. It does not explain top-level parameters such as project_id, title, currency, tax_percent, or contingency_percent, although their names are fairly self-explanatory. This is partial compensation, not complete coverage.

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 specific verb ('Save') and resource ('auditable draft estimate'), making the primary action unmistakable. It explicitly delimits scope with 'never send, approve, or accept it', which clearly distinguishes it from any finalization or approval workflow. Given the sibling tools are different resource types (change order, daily log, project), this is sufficient.

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?

The description gives clear context: use this tool to persist a draft estimate that must not proceed to sending, approval, or acceptance. However, it does not explicitly name sibling alternatives or state conditions for choosing this tool over them, such as 'use draft_change_order for change orders'. The usage guidance is mostly implied by the resource name and the negative boundary.

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