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

Annotations already declare this is a non-read, non-destructive, non-idempotent write, so the description is not carrying the safety burden alone. It still adds real context annotations cannot encode: the project is 'permanent' (irreversible) and 'costs nothing' (no billing impact).

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?

Two short sentences with zero filler; the action is front-loaded and the gating condition and behavioral facts follow immediately.

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 two-parameter create call with annotations present and no output schema, the description is nearly sufficient, covering purpose, precondition, and key behaviors. It omits the undocumented 'name' parameter and the failure mode when a slug already exists, which are the only real gaps.

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 only 50%: slug is documented in the schema, but name is not explained anywhere. The description adds no parameter meaning at all, so the half of the schema left bare remains bare.

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 and resource ('Create a project') and narrows the scope to 'one application', so the agent knows exactly what is produced. It also names the sibling rig.project.list, letting an agent distinguish it from read paths without opening a 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?

'Use when rig.project.list has none that fits' gives a concrete precondition and points at the alternative tool to check first. It stops short of stating exclusions or what to do on slug collisions, but the selection condition is unambiguous.

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