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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety needs no restating. The description instead adds non-annotation context: each item exposes kind and member count, collections are single-kind, older ones may hold video, results paginate via next_cursor, and the call is free. Only the cost of the call and the pagination mechanics go beyond annotations, and both are genuinely useful.

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-loaded with the usage trigger, then exclusions, then domain facts, then pagination — good ordering with no filler. The telegraphic sentence fragments and the 'Price: Free' aside are compact but slightly clipped; a tighter phrasing could fold the kind enumeration and filter guidance into one clause.

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?

An output schema exists, so return shape needs no prose; the description still volunteers that each collection reports kind and member count. For a zero-required-param list tool the coverage is strong, with the only real hole being the undocumented 'limit' parameter.

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 carries the burden. It explains the kind filter and enumerates the kind domain, and explains paging via 'next_cursor pages' (though the parameter is named 'cursor', a minor naming slippage). The 'limit' parameter is never mentioned, leaving one of three parameters undefined in both schema and description.

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?

Names the resource precisely ('Collections'), defines it in-line as 'named sets of Trackers such as Competitors', and states what each item carries (kind, member count). It also explicitly separates itself from list_trackers and get_changes, so an agent can route correctly without opening any 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?

Opens with an explicit 'Use when' trigger and then gives two negative cases with the exact alternative to call instead ('Not for its Trackers: list_trackers', 'Not for what changed in one: get_changes with collection'). This is the full when/when-not/alternative triad.

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