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

Beyond the annotations, it discloses that the result is a DRAFT-only document with no sending side effect, that eligibility is plan-gated, and that the call consumes the daily AI limit — meaningful quota and scope facts an agent cannot read from the schema. It does not address what happens on repeated calls, which matters given idempotentHint=false.

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?

Four short sentences, each load-bearing: what it produces, safety boundary, eligibility, and cost. The core action and output are front-loaded before the caveats.

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 single-parameter drafting tool with no output schema, the description covers the input precondition, the artifact produced, the non-destructive boundary, plan gating, and quota cost. Nothing an agent needs in order to decide whether to call it is missing.

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% and the single parameter is fully documented, so the schema baseline applies. The description adds the meaningful precondition that the referenced project must already carry a saved estimate, which constrains the valid project_id beyond the schema text.

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 a specific verb and resource ('Drafts a client proposal'), identifies the input source ('a project's saved estimate'), and states the output form ('saves it as a DRAFT document'). 'From a project's saved estimate' implicitly separates it from create_estimate, which produces that estimate.

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 clear eligibility conditions (account owners on plans that include documents) and an explicit boundary ('It never sends anything; the user reviews, edits and sends it on the Phulax website'). It stops short of naming a fallback sibling, e.g. 'call create_estimate first if no saved estimate exists', leaving that step to inference.

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