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

With no annotations, the description fully discloses behavior: polling until completion/failure/pause, early return with awaitingReview for caption-video, signed URL TTL (10 min) and re-fetch instruction, token costs for generative vs FFmpeg-lane, and the multi-output format. This exceeds what annotations would typically provide and gives the agent a complete mental model.

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 long but every sentence carries necessary information. It is front-loaded with the core behavior and return format, then covers caveats (timeout, URL expiry) and per-blueprint details. For a tool with 15 blueprint variants, this density is justified and well-organized with clear bullet separators.

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?

Comprehensive for a complex tool: covers output types (single, multi-output), pause behavior, URL signing, token costs, upload URL acquisition, and alternative polling strategies. The presence of a nested `inputs` object and no output schema is compensated by exhaustive description of all input combinations and result fields. 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 100%, but the description adds substantial meaning: it enumerates every blueprint's required/optional input fields, allowed enum values (e.g., style options), and output behavior (e.g., multi-output vs single). This is far beyond the schema's terse 'Blueprint to run' and 'input fields keyed by name', making the description indispensable for correct invocation.

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 ('starts a blueprint run and polls until it completes') and clearly differentiates from siblings like run_blueprint (just starts) and get_blueprint_run (just polls). The description explicitly frames it as a one-shot convenience tool, making its purpose unambiguous.

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?

Explicitly provides when-to-use guidance: 'If your MCP client enforces a short per-request timeout... use run_blueprint + get_blueprint_run polling instead.' Also instructs when to use continue_blueprint_run after an awaiting_review pause. Per-blueprint input fields guide the agent on which parameters to supply for each slug, leaving no ambiguity about tool selection.

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