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

The description goes far beyond the basic readOnlyHint/destructiveHint annotations: it discloses that the operation is paid, how cost is computed, that confirm=false does not start anything, that confirm=true starts a render, that idempotency_key protects against double charges, and what each error means. This is exactly the contextual behavior an agent needs before invoking a paid, state-changing tool.

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?

Although the description is long, it is dense and front-loaded: the paid nature, the exclusive input requirement, cost formula, confirmation flow, retry rule, follow-up call, and parameter meanings are all packed into a compact structure. Every sentence contributes operational value, and none restate the schema in a redundant way.

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?

The description covers both branches of behavior (confirm=false and confirm=true), the returned fields (needs_confirmation, price, balance, video_id, status queued, idempotency_key), failure/retry behavior, and error-specific user actions. It also links to related tools (tegas_account, tegas_voices, tegas_write_scenario, tegas_wait_video) making it fully actionable.

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?

Input schema coverage is 0%, yet the description compensates for every parameter: scenario_id/scenario_text exclusivity, quality enum values, voice coming from tegas_voices, defaults for music/subtitles/watermark, the meaning of confirm, idempotency_key retry semantics, and reference_urls. It adds essential meaning beyond the schema field names and defaults.

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 opens with 'PAID. Start rendering a video' and immediately clarifies the two possible sources: 'a Tessa scenario (scenario_id) or your own scenario_text - exactly one of them.' It uses a specific verb, names the resource, and distinguishes the operation from sibling tools like edit or wait by describing the render-start action.

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 workflow guidance: pass duration_sec returned by tegas_write_scenario, call again with confirm=true only after explicit consent, retry with the same idempotency_key on failure, and 'Then call tegas_wait_video.' It also provides error-specific actions for insufficient_tokens, no_active_plan, and rate_limited, which gives the agent clear when-to and when-not-to territory.

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