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

Annotations cover only the safety profile (readOnlyHint=false, non-destructive, non-idempotent), so the description carries the real burden. It discloses the blocking semantics ('wait for their reply, ends this turn'), project scoping, and the returned project identity, all of which are not in the annotations.

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 sentences, front-loaded with the scoping constraint and the core action before the usage rule. The music example is verbose but earns its place as the only concrete instance, so only minor trimming is possible.

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?

With no output schema, the description must say what comes back, and it does ('returns the project identity with its result'). Combined with the blocking behavior and scoping, an agent has what it needs, though the shape of the reply payload is only loosely specified.

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 50%: project_id is documented in the schema, but the question parameter is not. The description compensates by prescribing the question's content and format for the music case ('list 2-4 exact library track titles'), giving real semantic guidance beyond 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 and resource ('Ask the user a specific question and wait for their reply') and adds the terminal behavior ('ends this turn'), which no sibling tool shares. An agent can immediately distinguish this from all the add_*/set_* editing tools.

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?

Gives an explicit trigger ('Use whenever a material choice genuinely belongs to the user') plus a concrete mandated case (background music) with a prescribed procedure. It stops short of naming an alternative or an explicit 'do not use' bound, so it lands below a 5.

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