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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds valuable behavioral context: it returns 'starts_on/ends_on for the next edition, the organiser source URL and the page to cite,' which explains what the output contains and that dates are resolved. It also mentions the read-only nature redundantly, but this does not contradict annotations. The extra detail about output fields goes beyond 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?

The description is a single, well-structured sentence that leads with the core purpose ('Food festivals with their next resolved dates'), then lists the filters and output fields. It is concise, with no wasted words, and front-loads the most important information. Every clause earns its place, making it easy for an agent to parse quickly.

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?

Given that an output schema exists (not shown here) and annotations cover safety, the description sufficiently explains what the tool does, its filtering options, and the nature of its results. It does not need to enumerate return types or edge cases, as those are documented elsewhere. The description is complete enough for an agent to understand when to call it, though it could mention pagination or defaults, but these are already in the schema.

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%, with each parameter having a detailed description, including examples (e.g., city slug or name, default values, and behavior like 'did_you_mean' for unknown cities). The description's mention of filtering by 'city, country, a date window and text' is a high-level summary that adds no new semantics beyond the schema. Since the schema already carries the parameter burden, the baseline 3 applies.

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 clearly states the tool provides 'Food festivals with their next resolved dates' and mentions filtering by city, country, date window, and text. It identifies the specific resource type (food festivals) and its output (starts_on/ends_on, source URL, citation page). It does not explicitly differentiate from sibling tools like 'experiences' or 'place', but the domain is distinct enough that an agent can infer the purpose. Score 4 because it is clear but lacks explicit sibling comparison.

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?

The description provides no guidance on when to use this tool versus alternatives. It simply describes its functionality without mentioning any conditions for selection or exclusions. For example, it doesn't say 'use this for food festivals; use experiences for other events.' The agent must infer usage solely from the tool name and description, which is insufficient.

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