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

Annotations only give readOnlyHint=false, destructiveHint=false and openWorldHint=true; the description adds meaningful context beyond them: the record stays as an unsent draft, so it is effectively reversible, and it states an auth prerequisite (API key with access). The draft/reversibility detail is genuinely useful and not derivable from the annotations.

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 scoping constraint is front-loaded, but the description duplicates itself: 'Draft estimate on a project from line items' is repeated as 'Creates a draft estimate on a project from line items,' and the 'nothing reaches the client' point is restated twice. Roughly a third of the text is redundant.

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 mutation tool with full schema coverage and annotations declaring non-destructive/open-world, the description covers the key unknowns: it produces an unsent draft, requires credentials, and routes delivery to send_document. With no output schema it needn't describe return values, so coverage is adequate.

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 100%, so the schema already documents project_id, title, and the items list. The description restates the item fields (description, quantity, unit price, taxable) but adds no format or syntax detail beyond what the schema provides; baseline 3 applies when the schema does the heavy lifting.

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 (create/draft), resource (estimate), and scope (on a project from line items), and explicitly separates itself from the sibling send_document by noting nothing reaches the client until sending. An agent can identify the operation without opening the schema.

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?

Names the delivery alternative ('until send_document emails it to the client') and clarifies this tool is safe to run without confirmation ('runs without asking'), which is actionable routing context. It does not address when to choose this over other creation tools like create_invoice, but the primary alternative is explicit.

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