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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), but the description adds context that is not in any structured field: billing is per returned row and limit caps cost, and results are user-generated content to be treated as untrusted. The untrusted-input and cost-model warnings are genuinely useful operational context.

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?

Four tight sentences, all front-loaded: ordering caveat first, then routing, then return shape, then billing/safety notes. Every sentence carries distinct information with no repetition of schema or annotation content.

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?

No output schema exists, but the description enumerates the returned fields (pk, title, display_artist, duration_in_ms, is_explicit), so the agent knows the response shape. For a single-param, annotation-covered read tool, nothing needed to call it correctly is missing.

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 100% with a single well-documented param, so baseline is 3, but the description adds meaning beyond the schema's 'Max rows to return' by tying limit to cost ('caps both rows and cost'). That is a real semantic addition for a billing-sensitive tool.

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+resource (list Instagram music tracks) with the exact ordering semantics ('ordered by track ID, highest first') and preempts the obvious misreading with 'this is not a popularity ranking.' It also names the sibling it is not (search_tracks), so an agent can distinguish it without opening either 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?

Explicitly gives the when-to-use case ('browse tracks in the database') and the alternative with its selecting condition ('use search_tracks to find a specific song or artist'). This is exactly the when/when-not/alternative structure.

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