generate_invoice_from_proposal

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

With no annotations, the description carries the full burden and does well: it discloses the output state (DRAFT, not posted to GL), the derivation logic (maps the selected pricing option's line items), and required module/scope. It does not address idempotency, duplicate-invoice handling, or what happens if the proposal is already invoiced. Squarely above average for an unannotated mutation tool.

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 front-loaded clauses: identity/scope, behavior/requirements, then verification. Each sentence earns its place. Slightly dense with em-dash and parenthetical asides, but no filler.

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-param creation tool with no output schema, the description covers state (draft), side effects (no GL posting), prerequisites (Sales module, write scope), and a verification path in lieu of describing the return value. It lacks detail on error/failure cases (e.g., unapproved proposal) and whether the returned invoice ID is surfaced.

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 100%, so the schema already documents due_date, terms_code, proposal_id, invoice_date, and both GL account overrides. The description adds only the high-level notion that line items come from 'the selected pricing option', with no guidance on the GL override params. Baseline 3 is correct 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?

The description gives a specific verb+resource ('Generate a DRAFT AR invoice from a signed/contracted proposal') and explicitly frames it as 'the Proposal → invoice bridge', which separates it from create_invoice, generate_invoice_from_job, and generate_recurring_invoice without the agent opening any 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?

It states the gating conditions ('Requires the Sales module and the write scope'), a pre-call workflow ('Confirm the proposal and terms with the user'), and a post-call action ('verify the created invoice with search_invoices or get_invoice'). It never explicitly says when to prefer create_invoice or generate_invoice_from_job instead, so it stops short of full alternative routing.

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