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

Annotations cover readOnly=false/openWorld=true, but the description adds real value beyond them: it saves a draft unless finalize=true, the invoice total is the sum of billed lines, it does not email, and it requires confirming with the user before each call plus an API key with app access. That said, the first two sentences repeat the same behavioral point verbatim, diluting the added context.

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?

Front-loads the core purpose well, but the opening two sentences are near-duplicates ('Invoice an active job by percent of progress or dollar amount...' / 'Invoices an active job by percent of progress or by dollar amount...'). The trailing confirmation and API-key sentences are useful but boilerplate and add length.

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 4-parameter write tool with no output schema, the description covers draft-vs-finalize behavior, the no-email boundary, the confirmation requirement, and the auth prerequisite. Nothing critical is missing, though the repetitive phrasing costs a point on efficiency.

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 baseline is 3. The description still adds one derived semantic not present in the schema, namely that the invoice amount equals the sum of the billed lines, which helps an agent reason about partial billing, though method/finalize/lines otherwise restate the schema.

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 (invoice), the resource (an active job), and the two billing methods (percent of progress or dollar amount per line/contract line/change order). It explicitly distinguishes itself from the sibling knowify_send_invoice, so an agent can route correctly without opening either 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?

Clearly frames the context of use (invoicing an active job by progress or amount) and names the alternative for the delivery step: 'It does not email anyone; send_invoice does.' It lacks explicit when-not guidance (e.g., draft vs. finalized selection criteria), but the sibling routing is unambiguous.

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