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

Annotations already declare the safe read-only, idempotent, closed-world profile, so the bar is lower, yet the description adds real context: empty-query behavior and the shape of each result (id, requirements, duration, timing). It stops short of richer edge-case disclosure, but is solid beyond the structured fields.

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 purpose is front-loaded and the core is clear, but the middle sentence is an exhaustive catalog of individual effect names that inflates length well beyond what routing needs. Useful flavor for semantic matching, but several of those tokens do not earn their place.

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?

With no output schema, the description usefully summarizes what each result contains (id for apply_effect, requirements, duration, timing) and covers the empty-query case. It is nearly complete for a simple two-param search tool, missing only explicit alternative-tool routing.

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%, with the query and projectId parameters fully documented in-schema. The description mostly repeats the schema's own guidance (empty query lists all, query examples) with a mild addition on word count, so 3 is the correct baseline.

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 verb+resource ('Search Vidova's effects') and immediately clarifies the domain ('ready-made moments to put over a clip'). It also distinguishes itself from its key sibling by stating the result carries 'the id apply_effect takes', so an agent knows this is the lookup step before apply_effect.

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?

Provides practical query guidance ('Use one to three words', 'An empty query lists every effect') and implies the search-then-apply workflow via the apply_effect reference. However, it never explicitly says when to choose this over sibling search tools like search_templates, search_elements or search_library, leaving the routing to inference.

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