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

Annotations already declare a safe read-only, non-destructive, closed-world profile. The description adds real behavioral context beyond that: it accepts bounded planning metadata only, does not judge readiness, does not grant access, and labels omitted values as examples rather than inventing data.

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?

The when-to-use clause is front-loaded and strong, but the description runs long with several compound, comma-spliced sentences that fold triggers, semantics, and exclusions together. It is informative but denser than it needs to be.

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 an output schema present, the description needn't explain returns, and it covers scope, exclusions, and behavior for a 10-parameter tool adequately. Only minor gaps remain around how the group variables interact.

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% and four parameters carry enums, so the schema already documents every field thoroughly. The description reinforces the goal-to-group matching and omitted-value labeling but adds little parameter syntax beyond the schema, making the baseline 3 appropriate.

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 (planning line learning and cast preparation) tied to concrete triggers like 'learn my lines' and 'run lines', so the resource and scope are clear. It doesn't need to distinguish from siblings like get_practice_monologue since those are a different domain, but it also never names a sibling or a boundary against them.

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 explicit positive triggers (actor asking to learn lines, existing theatre/film cast, agency clients) and an explicit negative list (no casting decisions, private script import, surveillance, account access, saved sessions, subscription purchases). The conditions that select this tool are fully enumerated.

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