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

With annotations already covering readOnly/idempotent/destructive/openWorld, the description goes well beyond them: ranked results split group clips per rider, rides lacking a metric value are omitted, newest searches still return unmeasured clips, and every clip carries a viewer link. It also spells out the pagination protocol (pass next_cursor back as cursor with the same other arguments), which is the kind of behavior an agent cannot infer from schema alone.

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?

Effectively one dense paragraph but well ordered: purpose, then sort semantics, then filters, then pagination. Every sentence carries information, though the run-on density and quoted inline examples make it slightly harder to scan than a bulleted layout would be.

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 values need not be described, and the description still notes the viewer link. For a 10-parameter, zero-required, read-only search tool, sorting rules, filter dimensions, metric behavior, edge cases, and pagination are all covered — nothing needed to invoke 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%, so a 3 is the baseline, but the description adds real meaning: metric maps to 'biggest jumps, longest jumps, most airtime or fastest runs', feature accepts a feature or a run with examples, and cursor usage is described operationally ('with the same other arguments'). This is more than restating structured fields.

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?

Opens with a specific verb and resource plus a scope qualifier: 'Search public clips.' The surrounding detail (sorting, filtering, pagination) makes it unambiguous that this is the list/browse tool, cleanly separable from the singular retrieval sibling get_clip.

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?

Gives strong context: default is newest-first, ranked mode is selected by pairing sort 'biggest'/'smallest' with a metric, and it names the filterable dimensions (venue, feature, rider, when/since/until). It never explicitly contrasts itself with get_clip or list_venues, so it stops short of a full when/when-not routing statement.

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