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

Annotations already declare readOnlyHint and idempotentHint, but the description adds meaningful behavioral context: clips are quality-checked ('Every clip was checked to show someone actually doing the work'), the platform runs no background checks (important for privacy expectations), and the ordering logic based on city/state is disclosed. These details go beyond the annotations and help the agent understand what to expect from results.

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 front-loaded with the core purpose, then efficiently lists return fields, ordering behavior, and a critical caveat about background checks. Each sentence earns its place; there is no redundant fluff. While it is longer than some, the density of useful information is high, making it appropriately structured.

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?

Since there is no output schema, the description compensates by enumerating the returned data (watch page URL, embed URL, first name, town, search words, profile). It also covers the ordering behavior and the platform's stance on background checks. For a read-only tool with four parameters, this is comprehensive enough for an agent to call it correctly without additional assumptions.

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?

The schema already provides 100% coverage with descriptions for all four parameters. The tool description adds an extra layer of meaning, particularly for city and state: it explains how these parameters affect the ranking of clips (town-first, then state, then elsewhere), which is not in the schema. This richer contextual understanding of parameters justifies a score above the baseline 3.

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 states a specific verb and resource: 'Find short videos of locals doing a kind of job' with concrete examples like 'deck building' and 'pressure washing'. This clearly distinguishes it from sibling tools like search_local_workers or get_work_record, which focus on people or records rather than video clips. The purpose is unambiguous and actionable.

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 does not state conditions that favor find_work_clips over other tools, nor does it mention any exclusions or contexts where another tool would be more appropriate. The only usage-related hint is the optional city/state filtering, which is more about parameter behavior than tool selection.

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