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

With no annotations, the description carries the transparency burden. It discloses the return value, the refusal condition for due dates before the reference document's date, and the initial status ('It starts as planned'). This is strong, though it does not cover other potential failure modes or side effects beyond the stated validation rule.

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 short sentences, each carrying real information: the action and output, unit semantics, a validation constraint, and the initial lifecycle state. There is no filler or repeated schema boilerplate.

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 7-parameter tool with no output schema and no annotations, the description covers the essential non-schema facts: what is returned, one critical validation rule, and initial status. It does not fully explain all possible responses or failure modes, but the rich parameter schema covers the remaining input details.

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 high at 86%, so the schema already documents most parameters. The description mostly restates value_minor's net-of-VAT/minor-units semantics rather than adding new parameter-level meaning, so it earns the baseline 3 rather than higher.

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 states a specific action ('Add one dated deliverable'), a concrete resource, and what the tool returns ('its D number and the new counts'). This clearly distinguishes it from sibling tools like deliverable_delete and deliverable_status.

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?

Usage is implied by the verb 'Add' and the tool's name, but there is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named. The sibling tools are mutually exclusive enough that an agent can infer intent, but the description leaves that inference unstated.

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