suggest_clips

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

Despite no annotations, the description discloses behavioral rules and side effects. It states that suggestions must carry context and that clips opening on an answer without its question are rejected, with a concrete remedy ('widen start_second'). It also explains that the tool stores suggestions and pushes them to the UI, making the write operation explicit and transparent.

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 well-structured and front-loaded, starting with 'STEP 2 — Submit your clip suggestions' and then logically organizing prerequisites, rules, action, and follow-up. It is detailed but not redundant, with each section serving a purpose. The use of headings and imperative phrasing makes it easy to parse and contains no wasted sentences.

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 the lack of annotations and output schema, the description is remarkably complete. It covers the workflow (before, during, after), validation rules, and the eventual outcome (UI review). It provides enough context for an agent to know exactly how to use the tool and what constraints apply, leaving no critical information 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?

The schema already covers all parameter descriptions (100% coverage), but the tool description adds meaningful semantic context beyond that. For instance, it explains that 'context_line' does not satisfy the standalone check and that 'preview_text' must be the actual opening line. This enriches understanding of parameters like start_second and preview_text, elevating the baseline score from 3 to 4.

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's purpose: 'Submit your clip suggestions after analyzing the transcript.' It specifies the verb (submit) and resource (clip suggestions), and distinguishes it from siblings like 'create_clip' by framing it as a suggestion step that stores and pushes to UI for review. The 'What it does' section reinforces the unique action of storing suggestions and assigning clip numbers.

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 gives explicit usage context: 'Before calling this: read the transcript via get_ui_state(include_transcript: true) and identify the best viral moments.' It also explains the follow-up steps with 'After this: the user reviews in the UI. Then with batch_create_clips(export_selected: true) or create_clip(clip_number: N).' This clearly indicates when to use this tool relative to alternatives, providing a workflow and prerequisites.

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