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

With no annotations, the description carries full burden and delivers real behavioral facts: session continuity is automatic and server-maintained, calls may take 10-30 seconds for complex generation, and a SongPilotError is raised on network/auth failures. These are the traits an agent needs to set expectations. It does not detail rate limits or what 'session continuity' means across distinct clients, so not a 5.

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?

Front-loads purpose well and uses clear sections, but is bloated: the message examples are restated in the Examples block, the Returns prose and doctest duplicate each other, and the Note bullets repeat the session-continuity point already made under session_id. Roughly a third of the text is redundant.

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-entry orchestrator tool this is close to complete: request intent, session behavior, context hints, latency, and error mode are all covered. An output schema exists, so the description need not explain return values, yet it does so anyway without harm. Missing auth/permission expectations and any payload-size or rate constraints.

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 0%, so the description must compensate and it largely does: it explains message with concrete examples, explains session_id's optionality and explicit-reference purpose, and spells out the context object with a literal JSON example including currentPage/activeTab/focusedResource. It omits the ctx param (auto-injected, reasonably so) and does not formalize the context schema, keeping it from a 5.

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 ('Run the SongPilot orchestrator') and immediately clarifies the mechanism: routes requests to appropriate specialists (visual-director, manager, publicist). An agent knows exactly what this does and what class of tool it is. No siblings exist to distinguish from, but within its own scope it is precise.

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?

Declares itself 'the primary interface for interacting with SongPilot's AI system,' which tells the agent this is the default entry point, and the message examples show the range of accepted requests. There are no alternative tools to exclude and no when-not-to-use guidance, which caps it below a 5.

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