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

Goes well beyond the annotations (readOnly=false, destructive=false, openWorld=true) by disclosing the cost model (30 credits + 4 per started minute), the 2-hour ceiling, and the two-call quote/confirm safety flow where the first call 'nothing runs and nothing is charged'. That is exactly the kind of spend and side-effect disclosure an agent needs before invoking.

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 core behavior and cost before the routing and confirm details, and nearly every sentence carries operational weight. Slight waste in the trailing 'one yes covers the plan they approved (e.g. every line of an approved voice-over with the chosen voice)' example, which belongs to a voice-over tool and adds noise here.

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?

No output schema exists, and the description compensates by enumerating the return payload (ranked clips with start/end seconds, hook, caption, hashtags). For a 9-parameter credit-spending tool with no annotations covering cost, the description supplies limits, cost, prerequisites and the approval protocol — nothing an agent needs to call 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 89%, so the baseline is 3, but the description adds real meaning: clip length bounds (15-60 s), the 2-hour duration limit, the ranked output shape tied to count, and a full semantic explanation of confirm as a two-call approval gate. Minor gap: it never mentions the request, platform, language or idempotencyKey parameters, though the schema covers them adequately.

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 and resource: it picks ranked standalone moments (15-60 s reels) from a sentence-grouped transcript, returning start/end seconds, hook, caption and hashtags. It also explicitly distinguishes itself from plan_video_edit (single-piece edit) and from the default get_edit_playbook flow, so an agent can route correctly without opening a 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?

Gives explicit when/when-not: 'by default you pick the clips yourself following get_edit_playbook (free) — call this only when the user asks for Ignix's picker', plus the alternative plan_video_edit for a single-piece edit. The mandatory confirm-then-quote protocol is spelled out step by step, including what to tell the user and when a new approval is needed.

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