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

Well beyond the readOnly/idempotent annotations: it discloses that coverage is ~0.07% so an empty list means a gap rather than 'no gigs', requires attribution.line credit, mandates checking ambiguity.state before proceeding, and flags untrusted_text as display-only. Auth requirement ('linked') is also stated.

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?

Labeled fragments (Use / Inputs / Returns / Coverage / Auth) front-load the essential routing and format info with no filler. The telegraphic style is dense but slightly terse, packing several distinct obligations into run-on lines.

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, yet the description specifies the return shape (data.gigs[] with date, time, name, event_type, venue) and the available_cities[] fallback on a miss, plus the ambiguity check and auth state. An agent has everything needed to call it and interpret results.

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?

With 0% schema coverage the description carries the full burden and mostly delivers: key is defined as cluster_id from resolve_artist or a slug, city must be exact spelling, and from/to use YYYY-MM-DD. It does not state that key and city are mutually exclusive alternatives or whether from/to are optional/defaulted.

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 resource (upcoming gigs) and its two distinct lookup modes: one artist or one city within a date window. No sibling tool covers gigs, so the resource itself differentiates it from browse_artists, get_artist, get_festival, etc.

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: where or when an artist plays; what is on in a city' gives concrete situational triggers, and the key sourcing rule (cluster_id from resolve_artist) routes the agent through the correct sibling first. No explicit when-not or alternative-tool exclusions are given, but user intent cleanly maps to the two modes.

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